Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0457. Min Range: -6.0457
Max Act: 6.0457. Min Act: -0.1700
Data Index: 7819623 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.9520. Min Act: -0.1700
Data Index: 7549328 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.9207. Min Act: -0.1700
Data Index: 4924225 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.8582. Min Act: -0.1700
Data Index: 1646073 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.8270. Min Act: -0.1700
Data Index: 7243958 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.7645. Min Act: -0.1700
Data Index: 2398270 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.7020. Min Act: -0.1700
Data Index: 6816498 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.7332. Min Act: -0.1700
Data Index: 4842138 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.7332. Min Act: -0.1700
Data Index: 4997872 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.7020. Min Act: -0.1700
Data Index: 5243434 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.7020. Min Act: -0.1700
Data Index: 1892070 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.7020. Min Act: -0.1700
Data Index: 8127510 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.6707. Min Act: -0.1700
Data Index: 6835309 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.6395. Min Act: -0.1700
Data Index: 4036111 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.6707. Min Act: -0.1700
Data Index: 3642483 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.7020. Min Act: -0.1700
Data Index: 2674125 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.6395. Min Act: -0.1700
Data Index: 378732 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.6395. Min Act: -0.1700
Data Index: 3620024 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.6707. Min Act: -0.1700
Data Index: 6129310 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0457. Min Range: -6.0457
Max Act: 5.6395. Min Act: -0.1700
Data Index: 5120286 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #19