Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.9005. Min Act: -0.1700
Data Index: 69522 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.7754. Min Act: -0.1700
Data Index: 2929224 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.7911. Min Act: -0.1700
Data Index: 4529774 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6972. Min Act: -0.1700
Data Index: 3709357 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6659. Min Act: -0.1700
Data Index: 24390 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6816. Min Act: -0.1700
Data Index: 24395 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6659. Min Act: -0.1700
Data Index: 1483953 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6816. Min Act: -0.1700
Data Index: 3489505 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6659. Min Act: -0.1700
Data Index: 3786650 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6034. Min Act: -0.1700
Data Index: 5320375 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6347. Min Act: -0.1700
Data Index: 3577243 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6034. Min Act: -0.1700
Data Index: 5625576 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.6034. Min Act: -0.1700
Data Index: 3881262 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.5877. Min Act: -0.1700
Data Index: 7341307 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.5877. Min Act: -0.1700
Data Index: 3300452 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.5720. Min Act: -0.1700
Data Index: 5537056 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.5564. Min Act: -0.1700
Data Index: 1465668 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.5407. Min Act: -0.1700
Data Index: 3555334 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.5251. Min Act: -0.1700
Data Index: 546864 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9005. Min Range: -3.9005
Max Act: 3.5251. Min Act: -0.1700
Data Index: 2277006 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19