Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4039 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.6466. Min Act: -0.1700
Data Index: 4949898 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.6153. Min Act: -0.1700
Data Index: 5938871 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.5528. Min Act: -0.1700
Data Index: 770914 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.4903. Min Act: -0.1700
Data Index: 868182 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.4591. Min Act: -0.1700
Data Index: 5201784 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.4278. Min Act: -0.1700
Data Index: 7435164 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.4278. Min Act: -0.1700
Data Index: 572419 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3966. Min Act: -0.1700
Data Index: 2657882 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3966. Min Act: -0.1700
Data Index: 2657881 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3966. Min Act: -0.1700
Data Index: 5201793 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3966. Min Act: -0.1700
Data Index: 5201791 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3653. Min Act: -0.1700
Data Index: 8322571 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3653. Min Act: -0.1700
Data Index: 5201792 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3341. Min Act: -0.1700
Data Index: 5012673 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3341. Min Act: -0.1700
Data Index: 4649678 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3028. Min Act: -0.1700
Data Index: 4915580 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3028. Min Act: -0.1700
Data Index: 2342862 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3028. Min Act: -0.1700
Data Index: 4666884 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3028. Min Act: -0.1700
Data Index: 1969750 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6466. Min Range: -5.6466
Max Act: 5.3028. Min Act: -0.1700
Data Index: 6825702 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19