Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4385. Min Range: -8.4385
Max Act: 8.4385. Min Act: -0.1700
Data Index: 7249204 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4385. Min Range: -8.4385
Max Act: 8.4385. Min Act: -0.1700
Data Index: 8615036 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4385. Min Range: -8.4385
Max Act: 8.2510. Min Act: -0.1700
Data Index: 2893253 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4385. Min Range: -8.4385
Max Act: 8.1885. Min Act: -0.1700
Data Index: 4692553 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4385. Min Range: -8.4385
Max Act: 8.1260. Min Act: -0.1700
Data Index: 5261700 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.9385. Min Act: -0.1700
Data Index: 8063177 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4385. Min Range: -8.4385
Max Act: 8.0010. Min Act: -0.1700
Data Index: 8410616 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.9385. Min Act: -0.1700
Data Index: 4005730 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.8760. Min Act: -0.1700
Data Index: 892462 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.8135. Min Act: -0.1700
Data Index: 6937225 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.8135. Min Act: -0.1700
Data Index: 8419840 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.8135. Min Act: -0.1700
Data Index: 4246889 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.7510. Min Act: -0.1700
Data Index: 1269186 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.8135. Min Act: -0.1700
Data Index: 548797 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.7510. Min Act: -0.1700
Data Index: 8442858 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.6885. Min Act: -0.1700
Data Index: 472385 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.6885. Min Act: -0.1700
Data Index: 212339 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.6572. Min Act: -0.1700
Data Index: 7817497 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.6260. Min Act: -0.1700
Data Index: 7103726 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4385. Min Range: -8.4385
Max Act: 7.6260. Min Act: -0.1700
Data Index: 818109 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19