Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.4779. Min Act: -0.1700
Data Index: 5287366 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.5092. Min Act: -0.1700
Data Index: 3597988 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.2279. Min Act: -0.1700
Data Index: 5480528 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.2592. Min Act: -0.1700
Data Index: 2148220 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.2279. Min Act: -0.1700
Data Index: 1531534 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.1654. Min Act: -0.1700
Data Index: 4863579 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.1654. Min Act: -0.1700
Data Index: 4013029 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.1342. Min Act: -0.1700
Data Index: 840191 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.1029. Min Act: -0.1700
Data Index: 3231990 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.1029. Min Act: -0.1700
Data Index: 8313121 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0717. Min Act: -0.1700
Data Index: 7456974 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0717. Min Act: -0.1700
Data Index: 4319400 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0717. Min Act: -0.1700
Data Index: 7580949 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0717. Min Act: -0.1700
Data Index: 5493860 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0717. Min Act: -0.1700
Data Index: 2161781 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0404. Min Act: -0.1700
Data Index: 4055988 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0717. Min Act: -0.1700
Data Index: 6551552 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0404. Min Act: -0.1700
Data Index: 5565139 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0092. Min Act: -0.1700
Data Index: 4758093 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5092. Min Range: -6.5092
Max Act: 6.0404. Min Act: -0.1700
Data Index: 4110102 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19