Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2225 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4263. Min Range: -6.4263
Max Act: 6.4263. Min Act: -0.1700
Data Index: 5147264 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4263. Min Range: -6.4263
Max Act: 6.0825. Min Act: -0.1700
Data Index: 1133889 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.9263. Min Act: -0.1700
Data Index: 213887 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.8638. Min Act: -0.1700
Data Index: 2698859 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.8638. Min Act: -0.1700
Data Index: 1804306 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.8325. Min Act: -0.1700
Data Index: 310232 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.8013. Min Act: -0.1700
Data Index: 4169413 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.7700. Min Act: -0.1700
Data Index: 6841403 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.8013. Min Act: -0.1700
Data Index: 5387328 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.8013. Min Act: -0.1700
Data Index: 3020582 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.7700. Min Act: -0.1700
Data Index: 2508386 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.7700. Min Act: -0.1700
Data Index: 3556326 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.7388. Min Act: -0.1700
Data Index: 2572199 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.7388. Min Act: -0.1700
Data Index: 6371491 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.7388. Min Act: -0.1700
Data Index: 5223137 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.7075. Min Act: -0.1700
Data Index: 6253601 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.7388. Min Act: -0.1700
Data Index: 1501558 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.6763. Min Act: -0.1700
Data Index: 602925 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.6763. Min Act: -0.1700
Data Index: 7141655 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4263. Min Range: -6.4263
Max Act: 5.6763. Min Act: -0.1700
Data Index: 7330270 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19