Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.9202. Min Act: -0.1700
Data Index: 741625 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.9202. Min Act: -0.1700
Data Index: 8141030 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.9202. Min Act: -0.1700
Data Index: 3795922 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.8577. Min Act: -0.1700
Data Index: 2692420 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.6702. Min Act: -0.1700
Data Index: 8557855 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.6077. Min Act: -0.1700
Data Index: 894916 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.6077. Min Act: -0.1700
Data Index: 7080517 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.6077. Min Act: -0.1700
Data Index: 1964712 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.5452. Min Act: -0.1700
Data Index: 1382263 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.5452. Min Act: -0.1700
Data Index: 6590062 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.5452. Min Act: -0.1700
Data Index: 2997123 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.4827. Min Act: -0.1700
Data Index: 2493448 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.4827. Min Act: -0.1700
Data Index: 7980757 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.4827. Min Act: -0.1700
Data Index: 6786672 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.4827. Min Act: -0.1700
Data Index: 7850949 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.4202. Min Act: -0.1700
Data Index: 2478936 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.4202. Min Act: -0.1700
Data Index: 4805420 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.3577. Min Act: -0.1700
Data Index: 5118717 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.3577. Min Act: -0.1700
Data Index: 6054980 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9202. Min Range: -8.9202
Max Act: 8.3577. Min Act: -0.1700
Data Index: 6738273 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19