Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0029. Min Range: -8.0029
Max Act: 8.0029. Min Act: -0.1700
Data Index: 6767311 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.9404. Min Act: -0.1700
Data Index: 6818917 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.8466. Min Act: -0.1700
Data Index: 4655658 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.8466. Min Act: -0.1700
Data Index: 5244749 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.7841. Min Act: -0.1700
Data Index: 5941753 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.7529. Min Act: -0.1700
Data Index: 4070793 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.6904. Min Act: -0.1700
Data Index: 3302929 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.6904. Min Act: -0.1700
Data Index: 6581973 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.6904. Min Act: -0.1700
Data Index: 1951051 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.6279. Min Act: -0.1700
Data Index: 2933930 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.6591. Min Act: -0.1700
Data Index: 5383166 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.5966. Min Act: -0.1700
Data Index: 2417255 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.5654. Min Act: -0.1700
Data Index: 445028 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.5341. Min Act: -0.1700
Data Index: 5172156 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.5654. Min Act: -0.1700
Data Index: 3612815 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.5029. Min Act: -0.1700
Data Index: 3505632 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.4404. Min Act: -0.1700
Data Index: 2572110 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.4404. Min Act: -0.1700
Data Index: 2652835 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.3466. Min Act: -0.1700
Data Index: 1704294 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0029. Min Range: -8.0029
Max Act: 7.3779. Min Act: -0.1700
Data Index: 3680765 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19