Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.3461. Min Act: -0.1700
Data Index: 1035912 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.3147. Min Act: -0.1700
Data Index: 6181848 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.2991. Min Act: -0.1700
Data Index: 1223472 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.2834. Min Act: -0.1700
Data Index: 8679625 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.2519. Min Act: -0.1700
Data Index: 7149431 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.2676. Min Act: -0.1700
Data Index: 4844521 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.2676. Min Act: -0.1700
Data Index: 7835042 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.2362. Min Act: -0.1700
Data Index: 607822 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.2362. Min Act: -0.1700
Data Index: 7931948 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.2205. Min Act: -0.1700
Data Index: 2190431 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1891. Min Act: -0.1700
Data Index: 8697999 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1891. Min Act: -0.1700
Data Index: 2948128 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1733. Min Act: -0.1700
Data Index: 1008128 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1733. Min Act: -0.1700
Data Index: 4069897 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1733. Min Act: -0.1700
Data Index: 3678578 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1733. Min Act: -0.1700
Data Index: 73536 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1418. Min Act: -0.1700
Data Index: 224230 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1418. Min Act: -0.1700
Data Index: 35927 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1103. Min Act: -0.1700
Data Index: 1631751 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3461. Min Range: -3.3461
Max Act: 3.1103. Min Act: -0.1700
Data Index: 3316271 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19