Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1091 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0300. Min Range: -8.0300
Max Act: 8.0300. Min Act: -0.1700
Data Index: 3652261 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.5925. Min Act: -0.1700
Data Index: 3387508 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.5300. Min Act: -0.1700
Data Index: 7858407 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.4362. Min Act: -0.1700
Data Index: 8078661 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.4675. Min Act: -0.1700
Data Index: 4614679 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.3737. Min Act: -0.1700
Data Index: 7261444 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.3737. Min Act: -0.1700
Data Index: 3960161 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.3425. Min Act: -0.1700
Data Index: 2930549 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.3737. Min Act: -0.1700
Data Index: 2472695 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.3112. Min Act: -0.1700
Data Index: 2695515 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.3112. Min Act: -0.1700
Data Index: 6236256 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.3425. Min Act: -0.1700
Data Index: 8372479 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.3112. Min Act: -0.1700
Data Index: 1591728 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.3112. Min Act: -0.1700
Data Index: 4199589 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.2800. Min Act: -0.1700
Data Index: 1591729 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.2487. Min Act: -0.1700
Data Index: 131149 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.2487. Min Act: -0.1700
Data Index: 6834832 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.2487. Min Act: -0.1700
Data Index: 8035483 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.2487. Min Act: -0.1700
Data Index: 2577110 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0300. Min Range: -8.0300
Max Act: 7.2487. Min Act: -0.1700
Data Index: 496652 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19