Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1793 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2661. Min Range: -9.2661
Max Act: 9.2661. Min Act: -0.1700
Data Index: 7018150 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2661. Min Range: -9.2661
Max Act: 9.2036. Min Act: -0.1700
Data Index: 1761584 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2661. Min Range: -9.2661
Max Act: 9.1411. Min Act: -0.1700
Data Index: 6164380 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2661. Min Range: -9.2661
Max Act: 9.0786. Min Act: -0.1700
Data Index: 1128759 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2661. Min Range: -9.2661
Max Act: 9.0161. Min Act: -0.1700
Data Index: 1960744 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2661. Min Range: -9.2661
Max Act: 9.0161. Min Act: -0.1700
Data Index: 3039892 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.9536. Min Act: -0.1700
Data Index: 1472172 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.9536. Min Act: -0.1700
Data Index: 8690317 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.9536. Min Act: -0.1700
Data Index: 75734 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.9536. Min Act: -0.1700
Data Index: 3088737 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.8911. Min Act: -0.1700
Data Index: 7051105 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.8911. Min Act: -0.1700
Data Index: 5469081 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.8911. Min Act: -0.1700
Data Index: 4438405 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.9536. Min Act: -0.1700
Data Index: 4137549 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.9536. Min Act: -0.1700
Data Index: 3517721 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.9536. Min Act: -0.1700
Data Index: 636141 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.9536. Min Act: -0.1700
Data Index: 1806449 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.9536. Min Act: -0.1700
Data Index: 6912540 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.8911. Min Act: -0.1700
Data Index: 3774505 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2661. Min Range: -9.2661
Max Act: 8.8911. Min Act: -0.1700
Data Index: 3854851 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19