Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5121 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.3480. Min Act: -0.1700
Data Index: 1709734 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.2543. Min Act: -0.1700
Data Index: 1591389 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.1293. Min Act: -0.1700
Data Index: 1824373 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0980. Min Act: -0.1700
Data Index: 3386465 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0043. Min Act: -0.1700
Data Index: 3675491 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0355. Min Act: -0.1700
Data Index: 1546454 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3480. Min Range: -5.3480
Max Act: 5.0043. Min Act: -0.1700
Data Index: 545916 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9730. Min Act: -0.1700
Data Index: 6583779 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9418. Min Act: -0.1700
Data Index: 5143529 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9418. Min Act: -0.1700
Data Index: 4196905 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9418. Min Act: -0.1700
Data Index: 5242634 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9730. Min Act: -0.1700
Data Index: 8670050 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9418. Min Act: -0.1700
Data Index: 7924171 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9105. Min Act: -0.1700
Data Index: 5781053 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.9105. Min Act: -0.1700
Data Index: 4902341 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.8793. Min Act: -0.1700
Data Index: 5854145 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.8480. Min Act: -0.1700
Data Index: 63028 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.8793. Min Act: -0.1700
Data Index: 4312251 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.8480. Min Act: -0.1700
Data Index: 6771239 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3480. Min Range: -5.3480
Max Act: 4.8480. Min Act: -0.1700
Data Index: 4952068 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19