Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.9358. Min Act: -0.1700
Data Index: 3790031 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.9046. Min Act: -0.1700
Data Index: 3377054 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.9046. Min Act: -0.1700
Data Index: 8410948 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.7796. Min Act: -0.1700
Data Index: 7029160 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.7796. Min Act: -0.1700
Data Index: 5054723 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.7796. Min Act: -0.1700
Data Index: 4574106 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.7483. Min Act: -0.1700
Data Index: 1338928 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.7483. Min Act: -0.1700
Data Index: 3523441 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6858. Min Act: -0.1700
Data Index: 8831257 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.7171. Min Act: -0.1700
Data Index: 2427142 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6858. Min Act: -0.1700
Data Index: 2056281 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6858. Min Act: -0.1700
Data Index: 8567777 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6546. Min Act: -0.1700
Data Index: 4050198 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6546. Min Act: -0.1700
Data Index: 796242 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6546. Min Act: -0.1700
Data Index: 3125723 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6546. Min Act: -0.1700
Data Index: 6998127 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6546. Min Act: -0.1700
Data Index: 1139049 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6546. Min Act: -0.1700
Data Index: 1496550 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6546. Min Act: -0.1700
Data Index: 6040832 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9358. Min Range: -5.9358
Max Act: 5.6233. Min Act: -0.1700
Data Index: 1151923 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19