Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5304 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.4849. Min Act: -0.1700
Data Index: 5984386 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.3287. Min Act: -0.1700
Data Index: 3220270 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.3287. Min Act: -0.1700
Data Index: 2844080 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.1412. Min Act: -0.1700
Data Index: 2887564 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.1412. Min Act: -0.1700
Data Index: 6219210 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.1412. Min Act: -0.1700
Data Index: 1805180 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.1412. Min Act: -0.1700
Data Index: 4341770 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.1412. Min Act: -0.1700
Data Index: 6897201 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.1099. Min Act: -0.1700
Data Index: 1542904 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.1099. Min Act: -0.1700
Data Index: 6609503 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.1099. Min Act: -0.1700
Data Index: 118455 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.0787. Min Act: -0.1700
Data Index: 3154600 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.0787. Min Act: -0.1700
Data Index: 1576676 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.0787. Min Act: -0.1700
Data Index: 3347397 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.0474. Min Act: -0.1700
Data Index: 4449968 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.0474. Min Act: -0.1700
Data Index: 1611367 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.0474. Min Act: -0.1700
Data Index: 4819326 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.0474. Min Act: -0.1700
Data Index: 6390447 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.0474. Min Act: -0.1700
Data Index: 7039130 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4849. Min Range: -5.4849
Max Act: 5.0162. Min Act: -0.1700
Data Index: 4903728 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19