Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4014 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.9223. Min Act: -0.1700
Data Index: 5503450 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.8911. Min Act: -0.1700
Data Index: 531537 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.8285. Min Act: -0.1700
Data Index: 4406801 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.8129. Min Act: -0.1700
Data Index: 1414378 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.8129. Min Act: -0.1700
Data Index: 6873840 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.7816. Min Act: -0.1700
Data Index: 6133733 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.7034. Min Act: -0.1700
Data Index: 4568263 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.6721. Min Act: -0.1700
Data Index: 8122653 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.6095. Min Act: -0.1700
Data Index: 3739327 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.6252. Min Act: -0.1700
Data Index: 2252122 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.6252. Min Act: -0.1700
Data Index: 524715 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.6252. Min Act: -0.1700
Data Index: 1926413 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.6095. Min Act: -0.1700
Data Index: 7133837 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.6095. Min Act: -0.1700
Data Index: 1130002 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.5626. Min Act: -0.1700
Data Index: 6813853 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.5313. Min Act: -0.1700
Data Index: 3250072 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.4999. Min Act: -0.1700
Data Index: 3113063 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.5469. Min Act: -0.1700
Data Index: 4103820 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.4843. Min Act: -0.1700
Data Index: 2379768 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9223. Min Range: -3.9223
Max Act: 3.4843. Min Act: -0.1700
Data Index: 2023876 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19