Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1887 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.4664. Min Act: -0.1700
Data Index: 8119929 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.2476. Min Act: -0.1700
Data Index: 1754905 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.2164. Min Act: -0.1700
Data Index: 7330837 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.1539. Min Act: -0.1700
Data Index: 3877913 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.1226. Min Act: -0.1700
Data Index: 3310677 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.1226. Min Act: -0.1700
Data Index: 686507 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.1226. Min Act: -0.1700
Data Index: 5996513 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.0914. Min Act: -0.1700
Data Index: 8308737 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.0601. Min Act: -0.1700
Data Index: 5638462 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.0601. Min Act: -0.1700
Data Index: 2268605 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.0601. Min Act: -0.1700
Data Index: 6498199 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4664. Min Range: -5.4664
Max Act: 5.0289. Min Act: -0.1700
Data Index: 7627037 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4664. Min Range: -5.4664
Max Act: 4.9664. Min Act: -0.1700
Data Index: 5981986 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4664. Min Range: -5.4664
Max Act: 4.9976. Min Act: -0.1700
Data Index: 1102128 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4664. Min Range: -5.4664
Max Act: 4.9976. Min Act: -0.1700
Data Index: 3940349 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4664. Min Range: -5.4664
Max Act: 4.9976. Min Act: -0.1700
Data Index: 3461556 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4664. Min Range: -5.4664
Max Act: 4.9976. Min Act: -0.1700
Data Index: 3222170 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4664. Min Range: -5.4664
Max Act: 4.9664. Min Act: -0.1700
Data Index: 5109554 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4664. Min Range: -5.4664
Max Act: 4.9664. Min Act: -0.1700
Data Index: 3524924 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4664. Min Range: -5.4664
Max Act: 4.9664. Min Act: -0.1700
Data Index: 7735062 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19