Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.1293. Min Range: -15.1293
Max Act: 15.1293. Min Act: -0.1700
Data Index: 8392098 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.1293. Min Range: -15.1293
Max Act: 15.0668. Min Act: -0.1700
Data Index: 3412241 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.1293. Min Range: -15.1293
Max Act: 14.8793. Min Act: -0.1700
Data Index: 5819083 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.1293. Min Range: -15.1293
Max Act: 14.6918. Min Act: -0.1700
Data Index: 5766781 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.1293. Min Range: -15.1293
Max Act: 14.2543. Min Act: -0.1700
Data Index: 7283107 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.1293. Min Range: -15.1293
Max Act: 14.1918. Min Act: -0.1700
Data Index: 8158842 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.1293. Min Range: -15.1293
Max Act: 14.1918. Min Act: -0.1700
Data Index: 6474588 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.1293. Min Range: -15.1293
Max Act: 14.1293. Min Act: -0.1700
Data Index: 3412242 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.1293. Min Range: -15.1293
Max Act: 14.0668. Min Act: -0.1699
Data Index: 6373072 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.1293. Min Range: -15.1293
Max Act: 14.0043. Min Act: -0.1700
Data Index: 3070900 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.1293. Min Range: -15.1293
Max Act: 14.0043. Min Act: -0.1700
Data Index: 2273290 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.1293. Min Range: -15.1293
Max Act: 13.9418. Min Act: -0.1700
Data Index: 6190592 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.1293. Min Range: -15.1293
Max Act: 13.9418. Min Act: -0.1700
Data Index: 5617290 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.1293. Min Range: -15.1293
Max Act: 13.8168. Min Act: -0.1700
Data Index: 7760148 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.1293. Min Range: -15.1293
Max Act: 13.8793. Min Act: -0.1700
Data Index: 7142158 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.1293. Min Range: -15.1293
Max Act: 13.8168. Min Act: -0.1700
Data Index: 6460355 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.1293. Min Range: -15.1293
Max Act: 13.8168. Min Act: -0.1700
Data Index: 4006211 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.1293. Min Range: -15.1293
Max Act: 13.6918. Min Act: -0.1700
Data Index: 7032985 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.1293. Min Range: -15.1293
Max Act: 13.6918. Min Act: -0.1700
Data Index: 8312733 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.1293. Min Range: -15.1293
Max Act: 13.5668. Min Act: -0.1700
Data Index: 1350250 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19