Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3593 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.4321. Min Act: -0.1700
Data Index: 7893883 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.4321. Min Act: -0.1700
Data Index: 3999534 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.3071. Min Act: -0.1700
Data Index: 8482352 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1508. Min Act: -0.1700
Data Index: 6005038 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1821. Min Act: -0.1700
Data Index: 1113729 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1821. Min Act: -0.1700
Data Index: 275561 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1508. Min Act: -0.1700
Data Index: 2056703 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1821. Min Act: -0.1700
Data Index: 1567029 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1508. Min Act: -0.1700
Data Index: 6061741 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1196. Min Act: -0.1700
Data Index: 5003960 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1196. Min Act: -0.1700
Data Index: 5885386 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1196. Min Act: -0.1700
Data Index: 3241912 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1196. Min Act: -0.1700
Data Index: 341376 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1196. Min Act: -0.1700
Data Index: 6932952 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.1196. Min Act: -0.1700
Data Index: 3707418 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.0883. Min Act: -0.1700
Data Index: 7795187 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.0883. Min Act: -0.1700
Data Index: 5039344 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.0883. Min Act: -0.1700
Data Index: 2100080 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.0883. Min Act: -0.1700
Data Index: 8409533 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4321. Min Range: -5.4321
Max Act: 5.0883. Min Act: -0.1700
Data Index: 4741318 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19