Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.7099. Min Act: -0.1700
Data Index: 8799151 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1700
Data Index: 4463847 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1700
Data Index: 2710136 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1699
Data Index: 4691999 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1696
Data Index: 6162198 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1700
Data Index: 7032744 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.6161. Min Act: -0.1700
Data Index: 895229 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.5849. Min Act: -0.1700
Data Index: 2443562 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.5536. Min Act: -0.1700
Data Index: 7050335 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.4911. Min Act: -0.1700
Data Index: 2348134 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.5224. Min Act: -0.1700
Data Index: 6117530 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.5224. Min Act: -0.1700
Data Index: 5093284 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.5224. Min Act: -0.1700
Data Index: 8471840 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.5536. Min Act: -0.1700
Data Index: 2565420 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.4911. Min Act: -0.1700
Data Index: 2536838 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.5224. Min Act: -0.1700
Data Index: 3666170 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.5224. Min Act: -0.1700
Data Index: 6652919 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.4911. Min Act: -0.1700
Data Index: 1980185 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.4911. Min Act: -0.1699
Data Index: 395015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7099. Min Range: -5.7099
Max Act: 5.4911. Min Act: -0.1700
Data Index: 6425559 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19