Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2041 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.6316. Min Act: -0.1700
Data Index: 3419521 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.5066. Min Act: -0.1700
Data Index: 6253607 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.3816. Min Act: -0.1700
Data Index: 48084 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.2566. Min Act: -0.1700
Data Index: 5688204 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.2254. Min Act: -0.1700
Data Index: 777761 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.1941. Min Act: -0.1700
Data Index: 2634464 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.1004. Min Act: -0.1700
Data Index: 3854078 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.1004. Min Act: -0.1700
Data Index: 1228380 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.0066. Min Act: -0.1700
Data Index: 8272522 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6316. Min Range: -5.6316
Max Act: 5.0066. Min Act: -0.1700
Data Index: 1762430 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.9441. Min Act: -0.1700
Data Index: 1662209 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.9441. Min Act: -0.1700
Data Index: 6079608 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.9129. Min Act: -0.1700
Data Index: 3548461 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.9129. Min Act: -0.1700
Data Index: 3296997 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.9129. Min Act: -0.1700
Data Index: 1833671 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.8816. Min Act: -0.1700
Data Index: 976488 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.8816. Min Act: -0.1700
Data Index: 7534289 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.8816. Min Act: -0.1700
Data Index: 8389114 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.8504. Min Act: -0.1700
Data Index: 4933620 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6316. Min Range: -5.6316
Max Act: 4.8504. Min Act: -0.1700
Data Index: 4211381 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19