Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 972 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4622. Min Range: -9.4622
Max Act: 9.4622. Min Act: -0.1700
Data Index: 1360987 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4622. Min Range: -9.4622
Max Act: 8.0872. Min Act: -0.1700
Data Index: 2566382 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4622. Min Range: -9.4622
Max Act: 8.0872. Min Act: -0.1700
Data Index: 4883296 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4622. Min Range: -9.4622
Max Act: 8.0872. Min Act: -0.1700
Data Index: 1073867 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4622. Min Range: -9.4622
Max Act: 8.0247. Min Act: -0.1700
Data Index: 2776653 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.9622. Min Act: -0.1700
Data Index: 6647144 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.8685. Min Act: -0.1700
Data Index: 1880463 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.8372. Min Act: -0.1700
Data Index: 5351731 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.7747. Min Act: -0.1700
Data Index: 6442747 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.7747. Min Act: -0.1700
Data Index: 241755 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.8060. Min Act: -0.1700
Data Index: 6428437 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.7747. Min Act: -0.1700
Data Index: 6527759 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.7435. Min Act: -0.1700
Data Index: 7412941 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.7747. Min Act: -0.1700
Data Index: 1640282 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.7747. Min Act: -0.1700
Data Index: 1471711 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.7122. Min Act: -0.1700
Data Index: 6773604 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.7122. Min Act: -0.1700
Data Index: 691437 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.6810. Min Act: -0.1700
Data Index: 7922345 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.7122. Min Act: -0.1700
Data Index: 6004387 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4622. Min Range: -9.4622
Max Act: 7.6810. Min Act: -0.1700
Data Index: 869498 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19