Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.7927. Min Act: -0.1700
Data Index: 6959804 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.7927. Min Act: -0.1700
Data Index: 6675772 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6677. Min Act: -0.1700
Data Index: 1381182 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6365. Min Act: -0.1700
Data Index: 8598179 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6052. Min Act: -0.1700
Data Index: 8204010 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6365. Min Act: -0.1700
Data Index: 4106583 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6365. Min Act: -0.1700
Data Index: 5344050 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.5740. Min Act: -0.1700
Data Index: 4189764 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6052. Min Act: -0.1700
Data Index: 8031450 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6052. Min Act: -0.1700
Data Index: 3626325 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.5740. Min Act: -0.1700
Data Index: 721390 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6052. Min Act: -0.1700
Data Index: 7062284 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6052. Min Act: -0.1700
Data Index: 3333052 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.6052. Min Act: -0.1700
Data Index: 878875 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.5115. Min Act: -0.1700
Data Index: 4323936 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.5115. Min Act: -0.1700
Data Index: 7095295 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.5427. Min Act: -0.1700
Data Index: 997990 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.5115. Min Act: -0.1700
Data Index: 7082413 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.5115. Min Act: -0.1700
Data Index: 7159383 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7927. Min Range: -4.7927
Max Act: 4.5115. Min Act: -0.1700
Data Index: 3181978 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19