Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.9338. Min Act: -0.1700
Data Index: 6894602 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.7463. Min Act: -0.1700
Data Index: 7118345 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.5588. Min Act: -0.1700
Data Index: 8592570 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.5276. Min Act: -0.1700
Data Index: 2333205 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.3713. Min Act: -0.1700
Data Index: 6180519 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.3713. Min Act: -0.1700
Data Index: 3208332 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.3088. Min Act: -0.1700
Data Index: 3035803 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.3088. Min Act: -0.1700
Data Index: 19419 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.2151. Min Act: -0.1700
Data Index: 6874119 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.2463. Min Act: -0.1700
Data Index: 2342557 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1838. Min Act: -0.1700
Data Index: 6609537 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1838. Min Act: -0.1700
Data Index: 3284405 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1526. Min Act: -0.1700
Data Index: 8121586 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1526. Min Act: -0.1700
Data Index: 3511419 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1526. Min Act: -0.1700
Data Index: 3508401 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1526. Min Act: -0.1700
Data Index: 2568322 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1526. Min Act: -0.1700
Data Index: 7518929 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1526. Min Act: -0.1700
Data Index: 2302722 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1213. Min Act: -0.1700
Data Index: 8213411 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9338. Min Range: -7.9338
Max Act: 7.1213. Min Act: -0.1700
Data Index: 8161504 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19