Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4596 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3015. Min Range: -6.3015
Max Act: 6.3015. Min Act: -0.1700
Data Index: 4356151 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.9890. Min Act: -0.1700
Data Index: 1318443 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.9578. Min Act: -0.1700
Data Index: 5069177 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.9265. Min Act: -0.1700
Data Index: 6877278 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.9578. Min Act: -0.1700
Data Index: 2163473 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8953. Min Act: -0.1700
Data Index: 5259402 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8953. Min Act: -0.1700
Data Index: 694802 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8953. Min Act: -0.1700
Data Index: 4850712 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8953. Min Act: -0.1700
Data Index: 750879 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8953. Min Act: -0.1700
Data Index: 7971464 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8953. Min Act: -0.1700
Data Index: 5307120 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8640. Min Act: -0.1700
Data Index: 8523215 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8953. Min Act: -0.1700
Data Index: 4522696 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8640. Min Act: -0.1700
Data Index: 4983246 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8640. Min Act: -0.1700
Data Index: 8477818 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8953. Min Act: -0.1700
Data Index: 694815 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8640. Min Act: -0.1700
Data Index: 972770 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8328. Min Act: -0.1700
Data Index: 736354 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8640. Min Act: -0.1700
Data Index: 5259404 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3015. Min Range: -6.3015
Max Act: 5.8015. Min Act: -0.1700
Data Index: 953248 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19