Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4986 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0319. Min Range: -1.0319
Max Act: 1.0319. Min Act: -0.1700
Data Index: 7255149 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9972. Min Act: -0.1700
Data Index: 6952977 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0319. Min Range: -1.0319
Max Act: 1.0145. Min Act: -0.1700
Data Index: 622951 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9798. Min Act: -0.1700
Data Index: 3862087 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9625. Min Act: -0.1700
Data Index: 3601426 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9625. Min Act: -0.1700
Data Index: 4975620 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9453. Min Act: -0.1700
Data Index: 8017251 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9625. Min Act: -0.1699
Data Index: 7398757 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9453. Min Act: -0.1700
Data Index: 6598432 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9453. Min Act: -0.1700
Data Index: 601750 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9625. Min Act: -0.1700
Data Index: 5065702 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9281. Min Act: -0.1700
Data Index: 5705573 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9281. Min Act: -0.1700
Data Index: 1389020 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9109. Min Act: -0.1700
Data Index: 3973593 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9281. Min Act: -0.1700
Data Index: 1526291 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9453. Min Act: -0.1700
Data Index: 6359777 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9281. Min Act: -0.1700
Data Index: 2863866 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9281. Min Act: -0.1700
Data Index: 3617965 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9281. Min Act: -0.1700
Data Index: 6805001 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0319. Min Range: -1.0319
Max Act: 0.9109. Min Act: -0.1700
Data Index: 6653985 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19