Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1706 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1504. Min Range: -7.1504
Max Act: 7.1504. Min Act: -0.1700
Data Index: 8179173 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.9316. Min Act: -0.1700
Data Index: 835580 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.8691. Min Act: -0.1700
Data Index: 7414440 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.8066. Min Act: -0.1700
Data Index: 4423369 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.8066. Min Act: -0.1700
Data Index: 3545417 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.7441. Min Act: -0.1700
Data Index: 3075636 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.7754. Min Act: -0.1700
Data Index: 7918102 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.7129. Min Act: -0.1700
Data Index: 3545418 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.6816. Min Act: -0.1700
Data Index: 3868133 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.7129. Min Act: -0.1700
Data Index: 1971863 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.6816. Min Act: -0.1700
Data Index: 2946925 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.6504. Min Act: -0.1700
Data Index: 5824546 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.6191. Min Act: -0.1700
Data Index: 564304 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.5879. Min Act: -0.1700
Data Index: 2593243 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.5254. Min Act: -0.1700
Data Index: 8466613 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.5566. Min Act: -0.1700
Data Index: 6607845 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.5879. Min Act: -0.1700
Data Index: 1322248 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.5566. Min Act: -0.1700
Data Index: 3412810 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.5254. Min Act: -0.1700
Data Index: 4372258 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1504. Min Range: -7.1504
Max Act: 6.5254. Min Act: -0.1700
Data Index: 8122467 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19