Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.3362. Min Act: -0.1700
Data Index: 3428878 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.3205. Min Act: -0.1700
Data Index: 4635114 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.2420. Min Act: -0.1700
Data Index: 558977 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.2577. Min Act: -0.1700
Data Index: 3595541 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.2577. Min Act: -0.1700
Data Index: 4185698 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.2420. Min Act: -0.1700
Data Index: 6433728 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.2420. Min Act: -0.1700
Data Index: 3349842 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.2263. Min Act: -0.1700
Data Index: 1094456 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.2263. Min Act: -0.1700
Data Index: 7544222 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1948. Min Act: -0.1700
Data Index: 8747429 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1791. Min Act: -0.1700
Data Index: 1234001 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1948. Min Act: -0.1700
Data Index: 5312585 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1633. Min Act: -0.1700
Data Index: 2511344 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1633. Min Act: -0.1700
Data Index: 1665984 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1633. Min Act: -0.1700
Data Index: 1513692 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1633. Min Act: -0.1700
Data Index: 144925 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1633. Min Act: -0.1700
Data Index: 3993779 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1476. Min Act: -0.1700
Data Index: 5960354 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1476. Min Act: -0.1700
Data Index: 6552361 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3362. Min Range: -3.3362
Max Act: 3.1476. Min Act: -0.1700
Data Index: 8757603 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19