Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.8208. Min Act: -0.1700
Data Index: 3386398 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7896. Min Act: -0.1700
Data Index: 1053928 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7896. Min Act: -0.1700
Data Index: 4539194 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7896. Min Act: -0.1700
Data Index: 5471314 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7896. Min Act: -0.1700
Data Index: 2627235 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7583. Min Act: -0.1700
Data Index: 7271312 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7896. Min Act: -0.1700
Data Index: 2976458 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7583. Min Act: -0.1700
Data Index: 5746825 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7583. Min Act: -0.1700
Data Index: 321360 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7896. Min Act: -0.1700
Data Index: 8551836 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7270. Min Act: -0.1700
Data Index: 643860 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7270. Min Act: -0.1700
Data Index: 3488272 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7270. Min Act: -0.1700
Data Index: 5560950 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.7270. Min Act: -0.1700
Data Index: 1851145 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.6957. Min Act: -0.1700
Data Index: 370104 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.6957. Min Act: -0.1700
Data Index: 1203675 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.6957. Min Act: -0.1700
Data Index: 487185 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.6957. Min Act: -0.1700
Data Index: 5777134 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.6644. Min Act: -0.1700
Data Index: 2258963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8208. Min Range: -3.8208
Max Act: 3.6957. Min Act: -0.1700
Data Index: 2070667 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19