Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1456 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1914. Min Range: -7.1914
Max Act: 7.1914. Min Act: -0.1700
Data Index: 974648 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.9102. Min Act: -0.1700
Data Index: 1830563 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.8477. Min Act: -0.1700
Data Index: 2870445 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.7852. Min Act: -0.1700
Data Index: 3883434 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.7539. Min Act: -0.1700
Data Index: 6099810 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.6289. Min Act: -0.1700
Data Index: 1146691 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5977. Min Act: -0.1700
Data Index: 829281 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5977. Min Act: -0.1700
Data Index: 2854633 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5352. Min Act: -0.1700
Data Index: 2167598 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5352. Min Act: -0.1700
Data Index: 6803620 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5352. Min Act: -0.1700
Data Index: 2222012 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5352. Min Act: -0.1700
Data Index: 998355 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5039. Min Act: -0.1700
Data Index: 2502981 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5039. Min Act: -0.1700
Data Index: 4765754 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5039. Min Act: -0.1700
Data Index: 3108054 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.5352. Min Act: -0.1700
Data Index: 2561190 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.4727. Min Act: -0.1700
Data Index: 3073111 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.4727. Min Act: -0.1700
Data Index: 1664222 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.4727. Min Act: -0.1700
Data Index: 3997494 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1914. Min Range: -7.1914
Max Act: 6.4414. Min Act: -0.1700
Data Index: 5123549 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19