Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.8147. Min Act: -0.1700
Data Index: 2937150 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.5022. Min Act: -0.1700
Data Index: 661844 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.3147. Min Act: -0.1700
Data Index: 6549933 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.2522. Min Act: -0.1700
Data Index: 3649701 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.3772. Min Act: -0.1700
Data Index: 8215333 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.2522. Min Act: -0.1700
Data Index: 7181626 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.2522. Min Act: -0.1700
Data Index: 1308760 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.1272. Min Act: -0.1700
Data Index: 6872542 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.0647. Min Act: -0.1700
Data Index: 840621 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.0647. Min Act: -0.1698
Data Index: 3724677 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.0334. Min Act: -0.1700
Data Index: 4281693 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.0334. Min Act: -0.1700
Data Index: 5766814 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8147. Min Range: -8.8147
Max Act: 8.0334. Min Act: -0.1700
Data Index: 5634352 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8147. Min Range: -8.8147
Max Act: 7.9397. Min Act: -0.1700
Data Index: 5188163 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8147. Min Range: -8.8147
Max Act: 7.9709. Min Act: -0.1700
Data Index: 3829662 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8147. Min Range: -8.8147
Max Act: 7.9084. Min Act: -0.1700
Data Index: 5166743 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8147. Min Range: -8.8147
Max Act: 7.8772. Min Act: -0.1700
Data Index: 861010 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8147. Min Range: -8.8147
Max Act: 7.8772. Min Act: -0.1700
Data Index: 3876770 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8147. Min Range: -8.8147
Max Act: 7.8772. Min Act: -0.1700
Data Index: 3724674 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8147. Min Range: -8.8147
Max Act: 7.8459. Min Act: -0.1700
Data Index: 3606819 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19