Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.8969. Min Act: -0.1700
Data Index: 7734124 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.8799. Min Act: -0.1700
Data Index: 8225731 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.8456. Min Act: -0.1700
Data Index: 5129 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.8199. Min Act: -0.1700
Data Index: 7735777 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.8199. Min Act: -0.1700
Data Index: 3738983 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.8113. Min Act: -0.1700
Data Index: 7247383 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.8113. Min Act: -0.1700
Data Index: 5834704 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7941. Min Act: -0.1698
Data Index: 6341691 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.8027. Min Act: -0.1700
Data Index: 4348334 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7769. Min Act: -0.1700
Data Index: 7247387 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7769. Min Act: -0.1700
Data Index: 2295233 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7769. Min Act: -0.1700
Data Index: 4701109 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7683. Min Act: -0.1700
Data Index: 1989401 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7683. Min Act: -0.1700
Data Index: 8387455 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7769. Min Act: -0.1700
Data Index: 4285354 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7769. Min Act: -0.1698
Data Index: 5392891 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7683. Min Act: -0.1700
Data Index: 2157962 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7596. Min Act: -0.1700
Data Index: 876309 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7596. Min Act: -0.1700
Data Index: 8173052 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8969. Min Range: -1.8969
Max Act: 1.7424. Min Act: -0.1700
Data Index: 6242226 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19