Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9147. Min Range: -6.9147
Max Act: 6.9147. Min Act: -0.1700
Data Index: 29747 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9147. Min Range: -6.9147
Max Act: 6.5709. Min Act: -0.1700
Data Index: 1668039 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9147. Min Range: -6.9147
Max Act: 6.3209. Min Act: -0.1700
Data Index: 1391867 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9147. Min Range: -6.9147
Max Act: 6.1022. Min Act: -0.1700
Data Index: 1981162 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9147. Min Range: -6.9147
Max Act: 6.0709. Min Act: -0.1700
Data Index: 2990345 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9147. Min Range: -6.9147
Max Act: 6.0709. Min Act: -0.1700
Data Index: 2691730 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9147. Min Range: -6.9147
Max Act: 6.0709. Min Act: -0.1700
Data Index: 5121984 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9147. Min Range: -6.9147
Max Act: 6.0709. Min Act: -0.1700
Data Index: 8078712 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.9772. Min Act: -0.1700
Data Index: 5879384 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.9772. Min Act: -0.1700
Data Index: 4477715 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.9459. Min Act: -0.1700
Data Index: 5648382 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.9147. Min Act: -0.1700
Data Index: 888406 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.8209. Min Act: -0.1700
Data Index: 3850451 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.8522. Min Act: -0.1700
Data Index: 7106456 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.8209. Min Act: -0.1700
Data Index: 4282121 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.8209. Min Act: -0.1700
Data Index: 2273324 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.8209. Min Act: -0.1700
Data Index: 3640895 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.8209. Min Act: -0.1700
Data Index: 2183607 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.7584. Min Act: -0.1700
Data Index: 580926 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9147. Min Range: -6.9147
Max Act: 5.7897. Min Act: -0.1700
Data Index: 2012137 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19