Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8282. Min Range: -5.8282
Max Act: 5.8282. Min Act: -0.1700
Data Index: 3542895 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8282. Min Range: -5.8282
Max Act: 5.1719. Min Act: -0.1700
Data Index: 3127916 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8282. Min Range: -5.8282
Max Act: 5.1719. Min Act: -0.1700
Data Index: 8488365 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8282. Min Range: -5.8282
Max Act: 5.1719. Min Act: -0.1700
Data Index: 789264 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8282. Min Range: -5.8282
Max Act: 5.1094. Min Act: -0.1700
Data Index: 4783956 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8282. Min Range: -5.8282
Max Act: 5.0469. Min Act: -0.1700
Data Index: 4455760 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.9532. Min Act: -0.1700
Data Index: 5866438 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.9219. Min Act: -0.1700
Data Index: 4407748 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.8907. Min Act: -0.1700
Data Index: 3973333 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.8907. Min Act: -0.1700
Data Index: 4462228 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.8594. Min Act: -0.1700
Data Index: 6433499 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.8594. Min Act: -0.1700
Data Index: 6827623 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.8594. Min Act: -0.1700
Data Index: 148219 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.8594. Min Act: -0.1700
Data Index: 6765787 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.8282. Min Act: -0.1700
Data Index: 1978864 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.7969. Min Act: -0.1700
Data Index: 5819948 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.7969. Min Act: -0.1700
Data Index: 6818541 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.8282. Min Act: -0.1700
Data Index: 3134567 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.7969. Min Act: -0.1700
Data Index: 3828000 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8282. Min Range: -5.8282
Max Act: 4.7657. Min Act: -0.1700
Data Index: 3714482 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19