Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 358 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.2895. Min Act: -0.1700
Data Index: 5299814 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.2565. Min Act: -0.1700
Data Index: 3467535 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.2400. Min Act: -0.1700
Data Index: 4340119 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.2234. Min Act: -0.1700
Data Index: 3209084 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.2234. Min Act: -0.1700
Data Index: 2022644 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.2069. Min Act: -0.1700
Data Index: 611064 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.2069. Min Act: -0.1700
Data Index: 1231120 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1737. Min Act: -0.1700
Data Index: 8506469 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1903. Min Act: -0.1700
Data Index: 1686377 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1903. Min Act: -0.1700
Data Index: 170081 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1903. Min Act: -0.1700
Data Index: 2457501 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1903. Min Act: -0.1700
Data Index: 8266724 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1903. Min Act: -0.1700
Data Index: 7508212 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1737. Min Act: -0.1700
Data Index: 4323271 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1570. Min Act: -0.1700
Data Index: 2164932 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1570. Min Act: -0.1700
Data Index: 2639244 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1570. Min Act: -0.1700
Data Index: 6085037 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1903. Min Act: -0.1700
Data Index: 7043345 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1903. Min Act: -0.1700
Data Index: 7032590 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2895. Min Range: -2.2895
Max Act: 2.1737. Min Act: -0.1700
Data Index: 976145 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19