Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2077 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.7045. Min Act: -0.1700
Data Index: 4854583 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.7358. Min Act: -0.1700
Data Index: 4854586 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.5795. Min Act: -0.1700
Data Index: 1096079 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.4858. Min Act: -0.1700
Data Index: 3894648 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.2983. Min Act: -0.1700
Data Index: 4956878 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.3608. Min Act: -0.1700
Data Index: 5469629 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.2983. Min Act: -0.1700
Data Index: 4961095 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.2670. Min Act: -0.1700
Data Index: 3201035 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.2358. Min Act: -0.1700
Data Index: 4945328 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.2045. Min Act: -0.1700
Data Index: 4589846 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.2045. Min Act: -0.1700
Data Index: 324420 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.1733. Min Act: -0.1700
Data Index: 8310239 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.1733. Min Act: -0.1700
Data Index: 5722751 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.1733. Min Act: -0.1700
Data Index: 7663488 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.1420. Min Act: -0.1700
Data Index: 7544107 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.1420. Min Act: -0.1700
Data Index: 2908666 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.1107. Min Act: -0.1700
Data Index: 5149964 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.1107. Min Act: -0.1700
Data Index: 6602695 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.1107. Min Act: -0.1700
Data Index: 297219 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7358. Min Range: -4.7358
Max Act: 4.0795. Min Act: -0.1700
Data Index: 2352132 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19