Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2792 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.6206. Min Act: -0.1700
Data Index: 56114 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.5893. Min Act: -0.1700
Data Index: 3390274 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.2768. Min Act: -0.1700
Data Index: 673506 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.3081. Min Act: -0.1700
Data Index: 2304708 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.2768. Min Act: -0.1700
Data Index: 8268133 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.1831. Min Act: -0.1700
Data Index: 1814670 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.1831. Min Act: -0.1700
Data Index: 5944456 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.1206. Min Act: -0.1700
Data Index: 360985 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.0268. Min Act: -0.1700
Data Index: 5159080 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.0581. Min Act: -0.1700
Data Index: 247343 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.0268. Min Act: -0.1700
Data Index: 18889 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6206. Min Range: -7.6206
Max Act: 7.0268. Min Act: -0.1700
Data Index: 4615269 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6206. Min Range: -7.6206
Max Act: 6.9956. Min Act: -0.1700
Data Index: 188455 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6206. Min Range: -7.6206
Max Act: 6.9643. Min Act: -0.1700
Data Index: 4887311 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6206. Min Range: -7.6206
Max Act: 6.9643. Min Act: -0.1700
Data Index: 3474737 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6206. Min Range: -7.6206
Max Act: 6.9331. Min Act: -0.1700
Data Index: 6139820 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6206. Min Range: -7.6206
Max Act: 6.9018. Min Act: -0.1700
Data Index: 4709940 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6206. Min Range: -7.6206
Max Act: 6.9018. Min Act: -0.1700
Data Index: 2945904 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6206. Min Range: -7.6206
Max Act: 6.9018. Min Act: -0.1700
Data Index: 6287637 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6206. Min Range: -7.6206
Max Act: 6.9018. Min Act: -0.1700
Data Index: 2852113 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19