Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2382 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.4690. Min Act: -0.1700
Data Index: 1035413 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.2190. Min Act: -0.1700
Data Index: 8198996 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.2190. Min Act: -0.1700
Data Index: 4214276 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.2190. Min Act: -0.1700
Data Index: 1330473 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.2190. Min Act: -0.1700
Data Index: 8348370 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.2190. Min Act: -0.1700
Data Index: 5526408 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.1565. Min Act: -0.1700
Data Index: 4738933 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.1565. Min Act: -0.1700
Data Index: 3423865 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0940. Min Act: -0.1700
Data Index: 8363612 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0940. Min Act: -0.1700
Data Index: 2619919 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0940. Min Act: -0.1700
Data Index: 7608577 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0940. Min Act: -0.1700
Data Index: 1395270 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0940. Min Act: -0.1700
Data Index: 5902434 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0940. Min Act: -0.1700
Data Index: 4345006 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0315. Min Act: -0.1700
Data Index: 3400385 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0315. Min Act: -0.1699
Data Index: 1610078 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0315. Min Act: -0.1700
Data Index: 5933407 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0315. Min Act: -0.1700
Data Index: 5958889 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0315. Min Act: -0.1700
Data Index: 6170447 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4690. Min Range: -8.4690
Max Act: 8.0315. Min Act: -0.1700
Data Index: 6597261 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19