Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3375 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3264. Min Range: -8.3264
Max Act: 8.3264. Min Act: -0.1700
Data Index: 6014276 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3264. Min Range: -8.3264
Max Act: 8.2639. Min Act: -0.1700
Data Index: 5615865 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3264. Min Range: -8.3264
Max Act: 8.2639. Min Act: -0.1700
Data Index: 8486517 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3264. Min Range: -8.3264
Max Act: 8.2639. Min Act: -0.1700
Data Index: 420105 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3264. Min Range: -8.3264
Max Act: 8.2014. Min Act: -0.1700
Data Index: 5755737 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3264. Min Range: -8.3264
Max Act: 8.2014. Min Act: -0.1700
Data Index: 8331486 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3264. Min Range: -8.3264
Max Act: 8.1389. Min Act: -0.1700
Data Index: 3909135 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3264. Min Range: -8.3264
Max Act: 8.0764. Min Act: -0.1700
Data Index: 7645774 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3264. Min Range: -8.3264
Max Act: 8.0139. Min Act: -0.1700
Data Index: 864061 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.9514. Min Act: -0.1700
Data Index: 7262611 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.8889. Min Act: -0.1700
Data Index: 8418121 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.8889. Min Act: -0.1700
Data Index: 4990119 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.8264. Min Act: -0.1700
Data Index: 4456113 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.8889. Min Act: -0.1700
Data Index: 2242981 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.8889. Min Act: -0.1700
Data Index: 707644 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.8889. Min Act: -0.1700
Data Index: 2416118 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.8264. Min Act: -0.1700
Data Index: 1807207 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.8264. Min Act: -0.1700
Data Index: 8351791 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.8264. Min Act: -0.1700
Data Index: 4370796 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3264. Min Range: -8.3264
Max Act: 7.7639. Min Act: -0.1700
Data Index: 1352196 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19