Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5853 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.7090. Min Act: -0.1700
Data Index: 683350 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.6778. Min Act: -0.1700
Data Index: 3605243 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.6778. Min Act: -0.1700
Data Index: 6590607 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.4278. Min Act: -0.1700
Data Index: 754572 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.3965. Min Act: -0.1700
Data Index: 1276954 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.3965. Min Act: -0.1700
Data Index: 6779139 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.3653. Min Act: -0.1700
Data Index: 3254239 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.3653. Min Act: -0.1700
Data Index: 257069 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.3340. Min Act: -0.1700
Data Index: 1954020 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.3340. Min Act: -0.1700
Data Index: 3096730 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.3340. Min Act: -0.1700
Data Index: 6894585 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.3340. Min Act: -0.1700
Data Index: 6184742 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.3028. Min Act: -0.1700
Data Index: 595904 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.2715. Min Act: -0.1700
Data Index: 92105 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.2715. Min Act: -0.1700
Data Index: 3096728 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.2715. Min Act: -0.1700
Data Index: 5710996 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.2403. Min Act: -0.1700
Data Index: 1707668 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.2715. Min Act: -0.1700
Data Index: 5177341 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.2715. Min Act: -0.1700
Data Index: 3740774 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7090. Min Range: -5.7090
Max Act: 5.2090. Min Act: -0.1700
Data Index: 163409 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19