Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4435 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.7321. Min Act: -0.1700
Data Index: 8166305 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.7008. Min Act: -0.1700
Data Index: 6045796 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6696. Min Act: -0.1700
Data Index: 1359992 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6383. Min Act: -0.1700
Data Index: 8166303 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6383. Min Act: -0.1700
Data Index: 6294536 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6383. Min Act: -0.1700
Data Index: 8643858 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6383. Min Act: -0.1700
Data Index: 6991356 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.5758. Min Act: -0.1700
Data Index: 4439825 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6071. Min Act: -0.1700
Data Index: 8166300 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6383. Min Act: -0.1700
Data Index: 7756511 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6071. Min Act: -0.1700
Data Index: 3020901 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6071. Min Act: -0.1700
Data Index: 6312989 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6071. Min Act: -0.1700
Data Index: 1336099 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6071. Min Act: -0.1700
Data Index: 692237 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.5758. Min Act: -0.1700
Data Index: 6952379 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.5758. Min Act: -0.1700
Data Index: 8027532 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.6071. Min Act: -0.1700
Data Index: 1913083 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.5446. Min Act: -0.1700
Data Index: 512612 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.5758. Min Act: -0.1700
Data Index: 3187564 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7321. Min Range: -6.7321
Max Act: 6.5758. Min Act: -0.1700
Data Index: 2320382 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19