Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.8161. Min Act: -0.1700
Data Index: 567273 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7849. Min Act: -0.1700
Data Index: 646697 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7536. Min Act: -0.1700
Data Index: 2754346 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7536. Min Act: -0.1700
Data Index: 5886580 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7849. Min Act: -0.1700
Data Index: 8440866 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7224. Min Act: -0.1700
Data Index: 842872 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6911. Min Act: -0.1700
Data Index: 5581265 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6911. Min Act: -0.1700
Data Index: 5796612 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.7224. Min Act: -0.1700
Data Index: 6800052 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6599. Min Act: -0.1700
Data Index: 4598038 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6286. Min Act: -0.1700
Data Index: 4673953 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.6286. Min Act: -0.1700
Data Index: 865011 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 7252697 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 5548016 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 6702546 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 2831327 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 260298 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 1231892 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 2660578 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 3304958 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19