Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0587. Min Range: -8.0587
Max Act: 8.0587. Min Act: -0.1700
Data Index: 99498 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.9337. Min Act: -0.1700
Data Index: 568047 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.8712. Min Act: -0.1700
Data Index: 7635468 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.6524. Min Act: -0.1700
Data Index: 2483003 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.5274. Min Act: -0.1700
Data Index: 5381380 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.5274. Min Act: -0.1700
Data Index: 719625 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.4649. Min Act: -0.1700
Data Index: 4862110 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.4649. Min Act: -0.1700
Data Index: 7754262 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.4649. Min Act: -0.1700
Data Index: 158546 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.4024. Min Act: -0.1700
Data Index: 6084192 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.4024. Min Act: -0.1700
Data Index: 3648820 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.2774. Min Act: -0.1700
Data Index: 3746350 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.2774. Min Act: -0.1700
Data Index: 7169940 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.2774. Min Act: -0.1700
Data Index: 2661608 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.2462. Min Act: -0.1700
Data Index: 1700452 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.2462. Min Act: -0.1700
Data Index: 2178341 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.2149. Min Act: -0.1700
Data Index: 5539442 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.2149. Min Act: -0.1700
Data Index: 7017958 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.2149. Min Act: -0.1700
Data Index: 4404445 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0587. Min Range: -8.0587
Max Act: 7.2149. Min Act: -0.1700
Data Index: 3066725 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19