Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.7264. Min Act: -0.1700
Data Index: 1914915 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6951. Min Act: -0.1700
Data Index: 6710652 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6951. Min Act: -0.1700
Data Index: 6000275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6638. Min Act: -0.1700
Data Index: 347826 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6638. Min Act: -0.1700
Data Index: 2337522 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6638. Min Act: -0.1700
Data Index: 5324330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6638. Min Act: -0.1700
Data Index: 3909828 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6638. Min Act: -0.1700
Data Index: 8605502 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6638. Min Act: -0.1700
Data Index: 4612768 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6325. Min Act: -0.1700
Data Index: 6251712 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6325. Min Act: -0.1700
Data Index: 121576 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6325. Min Act: -0.1700
Data Index: 817672 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6325. Min Act: -0.1700
Data Index: 3350167 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6169. Min Act: -0.1700
Data Index: 6274913 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6169. Min Act: -0.1700
Data Index: 7825327 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6169. Min Act: -0.1700
Data Index: 2662424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6012. Min Act: -0.1700
Data Index: 3757858 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.6012. Min Act: -0.1700
Data Index: 3216053 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.5856. Min Act: -0.1700
Data Index: 7018561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7264. Min Range: -3.7264
Max Act: 3.5856. Min Act: -0.1700
Data Index: 1549522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19