Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 296 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.9938. Min Act: -0.1700
Data Index: 1984277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.7438. Min Act: -0.1700
Data Index: 6621413 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.7438. Min Act: -0.1700
Data Index: 3496052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.7438. Min Act: -0.1700
Data Index: 4351529 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.6188. Min Act: -0.1700
Data Index: 5437483 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.6500. Min Act: -0.1700
Data Index: 6034408 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.6188. Min Act: -0.1700
Data Index: 7561961 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.6188. Min Act: -0.1700
Data Index: 7918503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.6188. Min Act: -0.1700
Data Index: 3077494 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.5563. Min Act: -0.1700
Data Index: 620108 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.5875. Min Act: -0.1700
Data Index: 4460239 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.5875. Min Act: -0.1700
Data Index: 4460236 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.5875. Min Act: -0.1700
Data Index: 8477669 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.5875. Min Act: -0.1700
Data Index: 2371407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.6188. Min Act: -0.1700
Data Index: 4351534 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.4938. Min Act: -0.1700
Data Index: 1089340 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.5563. Min Act: -0.1700
Data Index: 1131077 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.5563. Min Act: -0.1700
Data Index: 4178034 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.5250. Min Act: -0.1700
Data Index: 2889397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9938. Min Range: -6.9938
Max Act: 6.5563. Min Act: -0.1700
Data Index: 5226951 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19