Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2776 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3394. Min Range: -7.3394
Max Act: 7.3394. Min Act: -0.1700
Data Index: 1946218 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3394. Min Range: -7.3394
Max Act: 7.2769. Min Act: -0.1700
Data Index: 5522840 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3394. Min Range: -7.3394
Max Act: 7.2457. Min Act: -0.1700
Data Index: 7428886 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3394. Min Range: -7.3394
Max Act: 7.1207. Min Act: -0.1700
Data Index: 8039933 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.9644. Min Act: -0.1700
Data Index: 3310514 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.9019. Min Act: -0.1700
Data Index: 2596227 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.8707. Min Act: -0.1700
Data Index: 4444128 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.8707. Min Act: -0.1700
Data Index: 865518 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.8707. Min Act: -0.1700
Data Index: 5143947 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.8394. Min Act: -0.1700
Data Index: 1151663 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.8394. Min Act: -0.1700
Data Index: 4665860 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.8394. Min Act: -0.1700
Data Index: 1066356 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.8082. Min Act: -0.1700
Data Index: 3441646 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.7769. Min Act: -0.1700
Data Index: 5499588 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.7457. Min Act: -0.1700
Data Index: 6496579 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.7457. Min Act: -0.1700
Data Index: 721022 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.6832. Min Act: -0.1700
Data Index: 160240 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.6832. Min Act: -0.1700
Data Index: 3561523 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.6832. Min Act: -0.1700
Data Index: 6366956 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3394. Min Range: -7.3394
Max Act: 6.6832. Min Act: -0.1700
Data Index: 4957455 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19