Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2864 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.3332. Min Act: -0.1700
Data Index: 7674395 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.2081. Min Act: -0.1700
Data Index: 5041178 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.2081. Min Act: -0.1700
Data Index: 3956121 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.1769. Min Act: -0.1700
Data Index: 5553971 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.1144. Min Act: -0.1700
Data Index: 7187032 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.1144. Min Act: -0.1700
Data Index: 5585794 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.1144. Min Act: -0.1700
Data Index: 5785100 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0831. Min Act: -0.1700
Data Index: 6005319 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.1144. Min Act: -0.1700
Data Index: 578415 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.1144. Min Act: -0.1700
Data Index: 1602161 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0831. Min Act: -0.1700
Data Index: 3530093 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0831. Min Act: -0.1700
Data Index: 4822503 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0831. Min Act: -0.1700
Data Index: 6701666 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0519. Min Act: -0.1700
Data Index: 8259006 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0519. Min Act: -0.1700
Data Index: 2397726 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0519. Min Act: -0.1700
Data Index: 743697 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0519. Min Act: -0.1700
Data Index: 3945981 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0206. Min Act: -0.1700
Data Index: 3297221 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0206. Min Act: -0.1700
Data Index: 578416 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3332. Min Range: -4.3332
Max Act: 4.0519. Min Act: -0.1700
Data Index: 5233108 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19