Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4146. Min Range: -8.4146
Max Act: 8.4146. Min Act: -0.1700
Data Index: 7903707 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4146. Min Range: -8.4146
Max Act: 8.3521. Min Act: -0.1700
Data Index: 2299837 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4146. Min Range: -8.4146
Max Act: 8.2271. Min Act: -0.1700
Data Index: 4569254 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4146. Min Range: -8.4146
Max Act: 8.1959. Min Act: -0.1700
Data Index: 3552276 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4146. Min Range: -8.4146
Max Act: 8.0084. Min Act: -0.1700
Data Index: 5665287 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.9771. Min Act: -0.1700
Data Index: 2585177 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.9146. Min Act: -0.1700
Data Index: 2863407 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.9146. Min Act: -0.1700
Data Index: 252804 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.9146. Min Act: -0.1700
Data Index: 1844353 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.8521. Min Act: -0.1700
Data Index: 126255 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.8209. Min Act: -0.1700
Data Index: 4306244 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.7896. Min Act: -0.1700
Data Index: 2141604 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.8209. Min Act: -0.1700
Data Index: 7837015 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.7896. Min Act: -0.1700
Data Index: 1656875 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.7584. Min Act: -0.1700
Data Index: 134529 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.7584. Min Act: -0.1700
Data Index: 29931 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.6959. Min Act: -0.1700
Data Index: 3890236 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.6646. Min Act: -0.1700
Data Index: 1107902 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.6646. Min Act: -0.1700
Data Index: 7781179 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4146. Min Range: -8.4146
Max Act: 7.6646. Min Act: -0.1700
Data Index: 2120949 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19