Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6018. Min Range: -10.6018
Max Act: 10.6018. Min Act: -0.1700
Data Index: 4040103 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6018. Min Range: -10.6018
Max Act: 10.4143. Min Act: -0.1700
Data Index: 4040100 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6018. Min Range: -10.6018
Max Act: 10.4143. Min Act: -0.1700
Data Index: 4040098 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6018. Min Range: -10.6018
Max Act: 10.2893. Min Act: -0.1700
Data Index: 4040094 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6018. Min Range: -10.6018
Max Act: 10.2268. Min Act: -0.1700
Data Index: 4040092 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6018. Min Range: -10.6018
Max Act: 10.2268. Min Act: -0.1700
Data Index: 4040093 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6018. Min Range: -10.6018
Max Act: 10.1643. Min Act: -0.1700
Data Index: 7578522 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6018. Min Range: -10.6018
Max Act: 10.1018. Min Act: -0.1700
Data Index: 4040095 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6018. Min Range: -10.6018
Max Act: 10.0393. Min Act: -0.1700
Data Index: 4040102 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.9143. Min Act: -0.1700
Data Index: 1094013 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.9143. Min Act: -0.1700
Data Index: 4040097 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.8518. Min Act: -0.1700
Data Index: 3359153 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.7893. Min Act: -0.1700
Data Index: 3780572 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.7268. Min Act: -0.1700
Data Index: 4040101 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.6643. Min Act: -0.1700
Data Index: 4040096 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.6643. Min Act: -0.1700
Data Index: 4669026 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.6018. Min Act: -0.1700
Data Index: 3337153 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.5393. Min Act: -0.1700
Data Index: 4040099 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.5393. Min Act: -0.1700
Data Index: 6454703 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6018. Min Range: -10.6018
Max Act: 9.4768. Min Act: -0.1700
Data Index: 6515699 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19