Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4070 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.2373. Min Act: -0.1700
Data Index: 7599569 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.2060. Min Act: -0.1700
Data Index: 3020777 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.2060. Min Act: -0.1700
Data Index: 6053959 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.1435. Min Act: -0.1700
Data Index: 137891 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.0810. Min Act: -0.1700
Data Index: 8162055 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.0498. Min Act: -0.1700
Data Index: 5329249 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.0185. Min Act: -0.1700
Data Index: 989867 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9560. Min Act: -0.1700
Data Index: 7718940 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9560. Min Act: -0.1700
Data Index: 3552882 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9560. Min Act: -0.1700
Data Index: 444058 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9248. Min Act: -0.1700
Data Index: 6053958 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9248. Min Act: -0.1700
Data Index: 1285924 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9248. Min Act: -0.1700
Data Index: 3245020 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8623. Min Act: -0.1700
Data Index: 4344451 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8935. Min Act: -0.1700
Data Index: 1598912 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8935. Min Act: -0.1700
Data Index: 7859801 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8310. Min Act: -0.1700
Data Index: 5177976 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8623. Min Act: -0.1700
Data Index: 4172779 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8623. Min Act: -0.1700
Data Index: 3933440 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8623. Min Act: -0.1700
Data Index: 4322725 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19