Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3128 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3303. Min Range: -6.3303
Max Act: 6.3303. Min Act: -0.1700
Data Index: 1928858 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3303. Min Range: -6.3303
Max Act: 6.1115. Min Act: -0.1700
Data Index: 5387387 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3303. Min Range: -6.3303
Max Act: 6.0178. Min Act: -0.1700
Data Index: 4609187 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3303. Min Range: -6.3303
Max Act: 6.0490. Min Act: -0.1700
Data Index: 7855558 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.9865. Min Act: -0.1700
Data Index: 3140378 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.9865. Min Act: -0.1700
Data Index: 1224896 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.9553. Min Act: -0.1700
Data Index: 4353034 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.9553. Min Act: -0.1700
Data Index: 7106921 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.9865. Min Act: -0.1700
Data Index: 5753505 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.9553. Min Act: -0.1700
Data Index: 1029291 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.9240. Min Act: -0.1700
Data Index: 4896806 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.8615. Min Act: -0.1700
Data Index: 8523036 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.8928. Min Act: -0.1700
Data Index: 6551555 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.8928. Min Act: -0.1700
Data Index: 8665179 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.8615. Min Act: -0.1700
Data Index: 7853340 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.8615. Min Act: -0.1700
Data Index: 8779466 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.8615. Min Act: -0.1700
Data Index: 8699160 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.8303. Min Act: -0.1700
Data Index: 2711195 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.8615. Min Act: -0.1700
Data Index: 6079231 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3303. Min Range: -6.3303
Max Act: 5.8303. Min Act: -0.1700
Data Index: 5456391 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19