Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1474 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.8331. Min Act: -0.1700
Data Index: 2287433 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.5206. Min Act: -0.1700
Data Index: 4007540 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.5206. Min Act: -0.1700
Data Index: 7159081 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.4581. Min Act: -0.1700
Data Index: 4030562 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.4893. Min Act: -0.1700
Data Index: 2974573 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.4581. Min Act: -0.1700
Data Index: 3830969 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.4581. Min Act: -0.1700
Data Index: 8105169 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.4268. Min Act: -0.1700
Data Index: 3714646 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.4581. Min Act: -0.1700
Data Index: 7919008 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.4268. Min Act: -0.1700
Data Index: 331848 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3956. Min Act: -0.1700
Data Index: 7622834 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3331. Min Act: -0.1700
Data Index: 6681726 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3643. Min Act: -0.1700
Data Index: 986161 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3331. Min Act: -0.1700
Data Index: 2826407 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3331. Min Act: -0.1700
Data Index: 8157625 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3018. Min Act: -0.1700
Data Index: 7049111 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3018. Min Act: -0.1700
Data Index: 3047816 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3018. Min Act: -0.1700
Data Index: 2515155 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3018. Min Act: -0.1700
Data Index: 3299115 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8331. Min Range: -6.8331
Max Act: 6.3018. Min Act: -0.1700
Data Index: 3491604 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19