Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0272. Min Range: -7.0272
Max Act: 7.0272. Min Act: -0.1700
Data Index: 8266640 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.8710. Min Act: -0.1700
Data Index: 5817043 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.7772. Min Act: -0.1700
Data Index: 799609 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.7460. Min Act: -0.1700
Data Index: 7329846 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.7460. Min Act: -0.1700
Data Index: 4126675 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.7147. Min Act: -0.1700
Data Index: 1275916 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.7147. Min Act: -0.1700
Data Index: 2809365 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.7460. Min Act: -0.1700
Data Index: 7265843 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.6835. Min Act: -0.1700
Data Index: 2738973 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.6210. Min Act: -0.1700
Data Index: 2389039 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.6210. Min Act: -0.1700
Data Index: 2338149 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.5897. Min Act: -0.1700
Data Index: 874845 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.5897. Min Act: -0.1700
Data Index: 7453287 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.5897. Min Act: -0.1700
Data Index: 6128493 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.5897. Min Act: -0.1700
Data Index: 4735017 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.5897. Min Act: -0.1700
Data Index: 1994497 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.5897. Min Act: -0.1700
Data Index: 544623 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.5897. Min Act: -0.1700
Data Index: 5276231 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.5897. Min Act: -0.1700
Data Index: 7329200 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0272. Min Range: -7.0272
Max Act: 6.5585. Min Act: -0.1700
Data Index: 2446610 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19