Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.7586. Min Act: -0.1700
Data Index: 3133645 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.3524. Min Act: -0.1700
Data Index: 6166326 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.3836. Min Act: -0.1700
Data Index: 6994647 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.3524. Min Act: -0.1700
Data Index: 5304517 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.1961. Min Act: -0.1700
Data Index: 4421571 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.1961. Min Act: -0.1700
Data Index: 2795551 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.1649. Min Act: -0.1700
Data Index: 8788525 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.1649. Min Act: -0.1700
Data Index: 4877269 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.1649. Min Act: -0.1700
Data Index: 2468000 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.1336. Min Act: -0.1700
Data Index: 8021614 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.1024. Min Act: -0.1700
Data Index: 8494659 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.1336. Min Act: -0.1700
Data Index: 6483423 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0399. Min Act: -0.1700
Data Index: 627893 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0399. Min Act: -0.1700
Data Index: 5257380 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0399. Min Act: -0.1700
Data Index: 6575934 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0086. Min Act: -0.1700
Data Index: 2679008 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0086. Min Act: -0.1700
Data Index: 5539324 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7586. Min Range: -6.7586
Max Act: 6.0086. Min Act: -0.1700
Data Index: 3632642 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.9774. Min Act: -0.1700
Data Index: 4842887 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7586. Min Range: -6.7586
Max Act: 5.9461. Min Act: -0.1700
Data Index: 750576 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19