Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1115 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.9623. Min Act: -0.1700
Data Index: 6643392 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.8061. Min Act: -0.1700
Data Index: 2656571 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.6498. Min Act: -0.1700
Data Index: 2410144 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.6186. Min Act: -0.1700
Data Index: 4711087 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.6186. Min Act: -0.1700
Data Index: 1629364 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.6498. Min Act: -0.1700
Data Index: 4263763 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.6498. Min Act: -0.1700
Data Index: 6409017 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.6186. Min Act: -0.1700
Data Index: 4259919 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.6186. Min Act: -0.1700
Data Index: 6627691 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.5873. Min Act: -0.1700
Data Index: 7102247 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.5248. Min Act: -0.1700
Data Index: 5474936 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.5873. Min Act: -0.1700
Data Index: 529719 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.5561. Min Act: -0.1700
Data Index: 162610 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.5561. Min Act: -0.1700
Data Index: 2354925 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.5248. Min Act: -0.1700
Data Index: 7893280 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.5873. Min Act: -0.1700
Data Index: 2462708 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.5248. Min Act: -0.1700
Data Index: 557343 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.5248. Min Act: -0.1700
Data Index: 1743462 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.4623. Min Act: -0.1700
Data Index: 4188339 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9623. Min Range: -4.9623
Max Act: 4.4936. Min Act: -0.1700
Data Index: 4166207 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19