Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.7253. Min Act: -0.1700
Data Index: 1725995 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.5690. Min Act: -0.1700
Data Index: 3662607 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.6003. Min Act: -0.1700
Data Index: 4556922 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.5690. Min Act: -0.1700
Data Index: 4917944 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.5690. Min Act: -0.1700
Data Index: 2539201 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.5065. Min Act: -0.1700
Data Index: 630317 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.4128. Min Act: -0.1700
Data Index: 4819267 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3815. Min Act: -0.1700
Data Index: 8723701 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3815. Min Act: -0.1700
Data Index: 6450015 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3815. Min Act: -0.1700
Data Index: 8150305 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3815. Min Act: -0.1700
Data Index: 5404338 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3503. Min Act: -0.1700
Data Index: 6136234 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3503. Min Act: -0.1700
Data Index: 2885289 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.3190. Min Act: -0.1700
Data Index: 5176207 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.2878. Min Act: -0.1700
Data Index: 7844469 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.2878. Min Act: -0.1700
Data Index: 1302210 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.2878. Min Act: -0.1700
Data Index: 466872 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.2878. Min Act: -0.1700
Data Index: 7703204 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.2565. Min Act: -0.1700
Data Index: 6382799 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7253. Min Range: -5.7253
Max Act: 5.2565. Min Act: -0.1700
Data Index: 3363777 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19