Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3600 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.9819. Min Act: -0.1700
Data Index: 7612131 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.7319. Min Act: -0.1700
Data Index: 3918651 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.7632. Min Act: -0.1700
Data Index: 1618553 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.7319. Min Act: -0.1700
Data Index: 2228602 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.7319. Min Act: -0.1700
Data Index: 7895618 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.6382. Min Act: -0.1700
Data Index: 3943273 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.6069. Min Act: -0.1700
Data Index: 5520091 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.5757. Min Act: -0.1700
Data Index: 130210 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.5444. Min Act: -0.1699
Data Index: 614462 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.5132. Min Act: -0.1700
Data Index: 344327 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.5444. Min Act: -0.1700
Data Index: 8072275 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.5132. Min Act: -0.1700
Data Index: 2925937 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.5132. Min Act: -0.1700
Data Index: 70660 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.5132. Min Act: -0.1700
Data Index: 7050111 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.4819. Min Act: -0.1700
Data Index: 4982271 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.4507. Min Act: -0.1700
Data Index: 5599296 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.4507. Min Act: -0.1700
Data Index: 3359197 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.4507. Min Act: -0.1700
Data Index: 5330540 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.4507. Min Act: -0.1700
Data Index: 6631067 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9819. Min Range: -6.9819
Max Act: 6.4507. Min Act: -0.1700
Data Index: 5152359 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19