Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.3143. Min Act: -0.1700
Data Index: 8233433 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.3143. Min Act: -0.1700
Data Index: 7520483 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.3143. Min Act: -0.1700
Data Index: 6458767 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.2979. Min Act: -0.1700
Data Index: 1112736 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.2814. Min Act: -0.1700
Data Index: 1627949 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.2649. Min Act: -0.1700
Data Index: 5890439 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.2814. Min Act: -0.1700
Data Index: 3781065 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.2319. Min Act: -0.1700
Data Index: 8735140 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.2484. Min Act: -0.1700
Data Index: 7512793 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.2319. Min Act: -0.1700
Data Index: 8059706 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.2319. Min Act: -0.1700
Data Index: 3156299 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.2153. Min Act: -0.1700
Data Index: 8654000 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.1987. Min Act: -0.1700
Data Index: 5768933 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.1987. Min Act: -0.1700
Data Index: 4239852 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.1821. Min Act: -0.1700
Data Index: 8059709 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.1821. Min Act: -0.1700
Data Index: 686127 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.1821. Min Act: -0.1700
Data Index: 4228258 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.1655. Min Act: -0.1700
Data Index: 4532469 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.1655. Min Act: -0.1700
Data Index: 5890435 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3143. Min Range: -2.3143
Max Act: 2.1488. Min Act: -0.1700
Data Index: 3009741 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19