Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.4615. Min Act: -0.1700
Data Index: 4556420 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.4453. Min Act: -0.1700
Data Index: 5510420 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.4290. Min Act: -0.1700
Data Index: 8498100 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.4290. Min Act: -0.1700
Data Index: 8543437 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.4127. Min Act: -0.1700
Data Index: 7350206 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.4127. Min Act: -0.1700
Data Index: 2953744 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3964. Min Act: -0.1700
Data Index: 6084902 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3964. Min Act: -0.1700
Data Index: 5367365 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3637. Min Act: -0.1700
Data Index: 8297265 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3964. Min Act: -0.1700
Data Index: 1907832 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3473. Min Act: -0.1700
Data Index: 5476155 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3637. Min Act: -0.1700
Data Index: 8275931 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3637. Min Act: -0.1700
Data Index: 6905219 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3801. Min Act: -0.1700
Data Index: 1477954 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3637. Min Act: -0.1700
Data Index: 4873314 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3309. Min Act: -0.1700
Data Index: 1164219 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3309. Min Act: -0.1700
Data Index: 3514539 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3309. Min Act: -0.1700
Data Index: 6438443 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3145. Min Act: -0.1700
Data Index: 4488244 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4615. Min Range: -2.4615
Max Act: 2.3309. Min Act: -0.1700
Data Index: 6538315 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19