Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6215 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1271. Min Range: -6.1271
Max Act: 6.1271. Min Act: -0.1700
Data Index: 1343274 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.9396. Min Act: -0.1700
Data Index: 382103 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.8459. Min Act: -0.1700
Data Index: 8355744 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.7209. Min Act: -0.1700
Data Index: 338680 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.7209. Min Act: -0.1700
Data Index: 1954299 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6896. Min Act: -0.1700
Data Index: 4246995 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6896. Min Act: -0.1700
Data Index: 2308276 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6896. Min Act: -0.1700
Data Index: 2187844 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6584. Min Act: -0.1700
Data Index: 653354 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6584. Min Act: -0.1700
Data Index: 6514206 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6271. Min Act: -0.1700
Data Index: 8514911 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5959. Min Act: -0.1700
Data Index: 3212467 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6271. Min Act: -0.1700
Data Index: 3750158 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5959. Min Act: -0.1700
Data Index: 5306200 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5959. Min Act: -0.1700
Data Index: 2010794 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6271. Min Act: -0.1700
Data Index: 1178406 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.6271. Min Act: -0.1700
Data Index: 2772201 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5646. Min Act: -0.1700
Data Index: 6223969 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5334. Min Act: -0.1700
Data Index: 2218309 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1271. Min Range: -6.1271
Max Act: 5.5646. Min Act: -0.1700
Data Index: 7609424 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19