Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2594 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.6399. Min Act: -0.1700
Data Index: 8016485 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.6077. Min Act: -0.1700
Data Index: 8008003 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.6238. Min Act: -0.1700
Data Index: 956027 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5916. Min Act: -0.1700
Data Index: 1538399 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5916. Min Act: -0.1700
Data Index: 3490802 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5755. Min Act: -0.1700
Data Index: 1821281 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5594. Min Act: -0.1700
Data Index: 6502629 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5755. Min Act: -0.1700
Data Index: 2743319 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5594. Min Act: -0.1700
Data Index: 7666102 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5755. Min Act: -0.1700
Data Index: 2442883 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5755. Min Act: -0.1700
Data Index: 2631476 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5755. Min Act: -0.1700
Data Index: 3396660 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5755. Min Act: -0.1700
Data Index: 5951559 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5433. Min Act: -0.1700
Data Index: 8549354 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5594. Min Act: -0.1700
Data Index: 358491 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5433. Min Act: -0.1700
Data Index: 3447098 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5594. Min Act: -0.1700
Data Index: 4279280 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5433. Min Act: -0.1700
Data Index: 1796861 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5433. Min Act: -0.1700
Data Index: 718614 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6399. Min Range: -2.6399
Max Act: 2.5271. Min Act: -0.1700
Data Index: 536118 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19