Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4131 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0420. Min Range: -3.0420
Max Act: 3.0420. Min Act: -0.1700
Data Index: 6966589 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0420. Min Range: -3.0420
Max Act: 3.0104. Min Act: -0.1700
Data Index: 954904 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9630. Min Act: -0.1700
Data Index: 5560826 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9471. Min Act: -0.1700
Data Index: 5250683 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9313. Min Act: -0.1700
Data Index: 7568544 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9313. Min Act: -0.1700
Data Index: 6241524 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.9313. Min Act: -0.1700
Data Index: 4771024 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8996. Min Act: -0.1700
Data Index: 5418784 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8996. Min Act: -0.1700
Data Index: 7123077 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8996. Min Act: -0.1700
Data Index: 4051941 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8679. Min Act: -0.1700
Data Index: 5506525 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8520. Min Act: -0.1700
Data Index: 2670063 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8520. Min Act: -0.1700
Data Index: 4435643 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8202. Min Act: -0.1700
Data Index: 2331387 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8520. Min Act: -0.1700
Data Index: 3174245 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8520. Min Act: -0.1700
Data Index: 2457091 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8361. Min Act: -0.1700
Data Index: 3296263 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8361. Min Act: -0.1700
Data Index: 5708792 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.8361. Min Act: -0.1700
Data Index: 3494118 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0420. Min Range: -3.0420
Max Act: 2.7883. Min Act: -0.1700
Data Index: 6427671 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19