Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1627 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.6330. Min Act: -0.1700
Data Index: 6601807 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.5080. Min Act: -0.1700
Data Index: 2717514 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.4454. Min Act: -0.1700
Data Index: 8483214 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.4454. Min Act: -0.1700
Data Index: 4744122 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.4142. Min Act: -0.1700
Data Index: 8002575 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.3829. Min Act: -0.1700
Data Index: 447338 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.3829. Min Act: -0.1700
Data Index: 3498148 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.3829. Min Act: -0.1700
Data Index: 1393795 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.3829. Min Act: -0.1700
Data Index: 5856705 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2892. Min Act: -0.1700
Data Index: 8110869 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2892. Min Act: -0.1700
Data Index: 6888489 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2579. Min Act: -0.1700
Data Index: 1020877 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2579. Min Act: -0.1700
Data Index: 7672356 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2267. Min Act: -0.1700
Data Index: 227484 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2579. Min Act: -0.1700
Data Index: 1521791 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2267. Min Act: -0.1700
Data Index: 4448674 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2267. Min Act: -0.1700
Data Index: 69314 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2267. Min Act: -0.1700
Data Index: 991119 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2267. Min Act: -0.1700
Data Index: 1409203 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6330. Min Range: -4.6330
Max Act: 4.2579. Min Act: -0.1700
Data Index: 2458797 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19