Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5657 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1092. Min Range: -9.1092
Max Act: 9.1092. Min Act: -0.1700
Data Index: 80691 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.7967. Min Act: -0.1700
Data Index: 5382430 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.7342. Min Act: -0.1700
Data Index: 4387736 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.7342. Min Act: -0.1700
Data Index: 3871717 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.7342. Min Act: -0.1700
Data Index: 8146175 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.7342. Min Act: -0.1700
Data Index: 6615399 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.6717. Min Act: -0.1700
Data Index: 1198722 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.5467. Min Act: -0.1700
Data Index: 8376916 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.6092. Min Act: -0.1700
Data Index: 8588414 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.6092. Min Act: -0.1700
Data Index: 3139165 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.5467. Min Act: -0.1700
Data Index: 3048532 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.5467. Min Act: -0.1700
Data Index: 7770896 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.5467. Min Act: -0.1700
Data Index: 807912 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.4842. Min Act: -0.1700
Data Index: 5226169 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.4842. Min Act: -0.1700
Data Index: 4114493 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.4842. Min Act: -0.1700
Data Index: 2350304 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.4842. Min Act: -0.1700
Data Index: 2052493 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.4217. Min Act: -0.1700
Data Index: 3998203 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.4217. Min Act: -0.1700
Data Index: 3236427 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1092. Min Range: -9.1092
Max Act: 8.4217. Min Act: -0.1700
Data Index: 4055440 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19