Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8431. Min Range: -7.8431
Max Act: 7.8431. Min Act: -0.1700
Data Index: 7496752 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8431. Min Range: -7.8431
Max Act: 7.4056. Min Act: -0.1700
Data Index: 1152437 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8431. Min Range: -7.8431
Max Act: 7.3431. Min Act: -0.1700
Data Index: 2056157 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8431. Min Range: -7.8431
Max Act: 7.0931. Min Act: -0.1700
Data Index: 2130199 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8431. Min Range: -7.8431
Max Act: 7.0618. Min Act: -0.1700
Data Index: 7382223 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8431. Min Range: -7.8431
Max Act: 7.0306. Min Act: -0.1700
Data Index: 2930675 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9993. Min Act: -0.1700
Data Index: 4702685 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9993. Min Act: -0.1700
Data Index: 8021916 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9993. Min Act: -0.1700
Data Index: 3848696 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9681. Min Act: -0.1700
Data Index: 7358507 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9681. Min Act: -0.1700
Data Index: 6760236 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9368. Min Act: -0.1700
Data Index: 7221768 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9368. Min Act: -0.1700
Data Index: 7791139 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9056. Min Act: -0.1700
Data Index: 746514 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9056. Min Act: -0.1700
Data Index: 8489332 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.9056. Min Act: -0.1700
Data Index: 131404 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.8431. Min Act: -0.1700
Data Index: 4021262 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.8431. Min Act: -0.1700
Data Index: 4342766 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.8431. Min Act: -0.1695
Data Index: 3833354 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8431. Min Range: -7.8431
Max Act: 6.8431. Min Act: -0.1700
Data Index: 350235 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19