Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4231 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.4695. Min Act: -0.1700
Data Index: 5991741 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.3757. Min Act: -0.1700
Data Index: 7687760 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2195. Min Act: -0.1700
Data Index: 6022517 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2195. Min Act: -0.1700
Data Index: 7848599 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.2195. Min Act: -0.1700
Data Index: 273017 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1570. Min Act: -0.1700
Data Index: 63100 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1257. Min Act: -0.1700
Data Index: 5204772 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0945. Min Act: -0.1700
Data Index: 7532796 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1257. Min Act: -0.1700
Data Index: 6439283 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.1257. Min Act: -0.1700
Data Index: 2935182 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0632. Min Act: -0.1700
Data Index: 6937845 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0945. Min Act: -0.1700
Data Index: 2550442 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0632. Min Act: -0.1700
Data Index: 530838 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0632. Min Act: -0.1700
Data Index: 4779976 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0632. Min Act: -0.1700
Data Index: 4599111 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0632. Min Act: -0.1700
Data Index: 4113951 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0632. Min Act: -0.1700
Data Index: 2230971 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0632. Min Act: -0.1700
Data Index: 7362027 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0320. Min Act: -0.1700
Data Index: 6462898 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4695. Min Range: -5.4695
Max Act: 5.0320. Min Act: -0.1700
Data Index: 1724864 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19