Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5553 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.8448. Min Act: -0.1700
Data Index: 7243991 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.6573. Min Act: -0.1700
Data Index: 5904119 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.5948. Min Act: -0.1700
Data Index: 5541248 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.5323. Min Act: -0.1700
Data Index: 3189851 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.4386. Min Act: -0.1700
Data Index: 3512740 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.3448. Min Act: -0.1700
Data Index: 4025623 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.3448. Min Act: -0.1700
Data Index: 3320357 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.2823. Min Act: -0.1700
Data Index: 7078444 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.2511. Min Act: -0.1700
Data Index: 956841 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.2198. Min Act: -0.1700
Data Index: 8533048 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.2198. Min Act: -0.1700
Data Index: 8616234 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.2198. Min Act: -0.1700
Data Index: 7270765 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.1261. Min Act: -0.1700
Data Index: 8414064 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.0948. Min Act: -0.1700
Data Index: 2838259 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.0948. Min Act: -0.1700
Data Index: 7652129 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.0948. Min Act: -0.1700
Data Index: 8691113 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.0636. Min Act: -0.1700
Data Index: 5559472 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.0636. Min Act: -0.1700
Data Index: 1378955 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.0636. Min Act: -0.1700
Data Index: 518861 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8448. Min Range: -7.8448
Max Act: 7.0636. Min Act: -0.1700
Data Index: 181075 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19