Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5897 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.3690. Min Act: -0.1700
Data Index: 997836 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.3065. Min Act: -0.1700
Data Index: 5151996 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.2753. Min Act: -0.1700
Data Index: 7015710 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.2440. Min Act: -0.1700
Data Index: 7300373 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.2440. Min Act: -0.1700
Data Index: 2055202 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.2128. Min Act: -0.1700
Data Index: 6672318 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.2128. Min Act: -0.1700
Data Index: 6767370 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.1190. Min Act: -0.1700
Data Index: 519016 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.1190. Min Act: -0.1700
Data Index: 6950079 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.1190. Min Act: -0.1700
Data Index: 3051149 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.1190. Min Act: -0.1700
Data Index: 3840051 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.0878. Min Act: -0.1700
Data Index: 5149901 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.0878. Min Act: -0.1700
Data Index: 597183 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.0565. Min Act: -0.1700
Data Index: 2534808 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.0565. Min Act: -0.1700
Data Index: 1427407 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.0253. Min Act: -0.1700
Data Index: 8563805 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3690. Min Range: -7.3690
Max Act: 6.9940. Min Act: -0.1700
Data Index: 4440905 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.0253. Min Act: -0.1700
Data Index: 1914810 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3690. Min Range: -7.3690
Max Act: 7.0253. Min Act: -0.1700
Data Index: 5761604 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3690. Min Range: -7.3690
Max Act: 6.9940. Min Act: -0.1700
Data Index: 3360419 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19