Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.9339. Min Act: -0.1700
Data Index: 5485701 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.9027. Min Act: -0.1700
Data Index: 8008977 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.8714. Min Act: -0.1700
Data Index: 6947571 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.8714. Min Act: -0.1700
Data Index: 6241790 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.8714. Min Act: -0.1700
Data Index: 6210399 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.8402. Min Act: -0.1700
Data Index: 1625205 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.8402. Min Act: -0.1700
Data Index: 7694879 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.8402. Min Act: -0.1700
Data Index: 5706983 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.8089. Min Act: -0.1700
Data Index: 190908 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.8089. Min Act: -0.1700
Data Index: 4827726 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.7777. Min Act: -0.1700
Data Index: 875960 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.7464. Min Act: -0.1700
Data Index: 4758790 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.7152. Min Act: -0.1700
Data Index: 8358887 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.7464. Min Act: -0.1700
Data Index: 3293290 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.6527. Min Act: -0.1700
Data Index: 544499 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.6839. Min Act: -0.1700
Data Index: 2704843 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.6839. Min Act: -0.1700
Data Index: 3106662 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.6839. Min Act: -0.1700
Data Index: 2352868 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.6527. Min Act: -0.1700
Data Index: 1353754 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9339. Min Range: -4.9339
Max Act: 4.6527. Min Act: -0.1700
Data Index: 3419040 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19