Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 12 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.7019. Min Act: -0.1700
Data Index: 5291160 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.3894. Min Act: -0.1700
Data Index: 6934344 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.4519. Min Act: -0.1700
Data Index: 5681123 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.3894. Min Act: -0.1700
Data Index: 3788689 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.2644. Min Act: -0.1700
Data Index: 6942816 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.2019. Min Act: -0.1700
Data Index: 62458 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.2644. Min Act: -0.1700
Data Index: 4879488 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.2644. Min Act: -0.1700
Data Index: 6439215 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.2019. Min Act: -0.1700
Data Index: 368974 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.2019. Min Act: -0.1700
Data Index: 6644135 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.2019. Min Act: -0.1700
Data Index: 4703571 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.2019. Min Act: -0.1700
Data Index: 8363473 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.1394. Min Act: -0.1700
Data Index: 283250 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.1394. Min Act: -0.1700
Data Index: 3979046 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.1394. Min Act: -0.1700
Data Index: 7680015 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.0769. Min Act: -0.1700
Data Index: 5821959 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.0769. Min Act: -0.1700
Data Index: 7084653 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.0769. Min Act: -0.1700
Data Index: 2419322 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.0144. Min Act: -0.1700
Data Index: 3633438 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7019. Min Range: -8.7019
Max Act: 8.0144. Min Act: -0.1700
Data Index: 6364140 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19