Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4552 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1227. Min Range: -5.1227
Max Act: 5.1227. Min Act: -0.1700
Data Index: 5876074 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1227. Min Range: -5.1227
Max Act: 5.0915. Min Act: -0.1700
Data Index: 5762399 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1227. Min Range: -5.1227
Max Act: 5.0602. Min Act: -0.1700
Data Index: 4546843 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1227. Min Range: -5.1227
Max Act: 5.0602. Min Act: -0.1700
Data Index: 6247299 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1227. Min Range: -5.1227
Max Act: 5.0290. Min Act: -0.1700
Data Index: 5714353 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1227. Min Range: -5.1227
Max Act: 5.0290. Min Act: -0.1700
Data Index: 5061694 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9977. Min Act: -0.1700
Data Index: 3357363 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1227. Min Range: -5.1227
Max Act: 5.0290. Min Act: -0.1700
Data Index: 782662 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9977. Min Act: -0.1700
Data Index: 6273490 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9977. Min Act: -0.1700
Data Index: 4440001 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9977. Min Act: -0.1700
Data Index: 7645273 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9977. Min Act: -0.1700
Data Index: 4457431 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9352. Min Act: -0.1700
Data Index: 8081090 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9352. Min Act: -0.1700
Data Index: 4027661 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9040. Min Act: -0.1700
Data Index: 2620298 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9040. Min Act: -0.1700
Data Index: 1950244 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.9040. Min Act: -0.1700
Data Index: 4599604 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.8727. Min Act: -0.1700
Data Index: 7679867 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.8415. Min Act: -0.1700
Data Index: 6813957 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1227. Min Range: -5.1227
Max Act: 4.8415. Min Act: -0.1700
Data Index: 5754294 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19