Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.2729. Min Act: -0.1700
Data Index: 21043 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.1792. Min Act: -0.1700
Data Index: 2663952 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.1792. Min Act: -0.1700
Data Index: 1966394 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.1479. Min Act: -0.1700
Data Index: 73484 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.0854. Min Act: -0.1700
Data Index: 2195221 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.0854. Min Act: -0.1700
Data Index: 4747819 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.0854. Min Act: -0.1700
Data Index: 4059211 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.0229. Min Act: -0.1700
Data Index: 5937397 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.0229. Min Act: -0.1700
Data Index: 7782484 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.0229. Min Act: -0.1700
Data Index: 2040091 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.0229. Min Act: -0.1700
Data Index: 3536813 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2729. Min Range: -6.2729
Max Act: 6.0542. Min Act: -0.1700
Data Index: 2478712 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2729. Min Range: -6.2729
Max Act: 5.9604. Min Act: -0.1700
Data Index: 2810622 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2729. Min Range: -6.2729
Max Act: 5.9917. Min Act: -0.1700
Data Index: 3727408 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2729. Min Range: -6.2729
Max Act: 5.9604. Min Act: -0.1700
Data Index: 7012903 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2729. Min Range: -6.2729
Max Act: 5.9292. Min Act: -0.1700
Data Index: 805935 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2729. Min Range: -6.2729
Max Act: 5.9292. Min Act: -0.1700
Data Index: 1079376 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2729. Min Range: -6.2729
Max Act: 5.9292. Min Act: -0.1700
Data Index: 1934032 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2729. Min Range: -6.2729
Max Act: 5.9292. Min Act: -0.1700
Data Index: 4602254 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2729. Min Range: -6.2729
Max Act: 5.8979. Min Act: -0.1700
Data Index: 2193536 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19