Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2002 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.1299. Min Act: -0.1700
Data Index: 605297 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.1299. Min Act: -0.1700
Data Index: 13358 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0797. Min Act: -0.1700
Data Index: 455939 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0797. Min Act: -0.1700
Data Index: 527375 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0797. Min Act: -0.1700
Data Index: 833311 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0461. Min Act: -0.1700
Data Index: 1193074 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0629. Min Act: -0.1700
Data Index: 640249 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0377. Min Act: -0.1700
Data Index: 629542 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0461. Min Act: -0.1700
Data Index: 207630 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0377. Min Act: -0.1700
Data Index: 1189292 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0293. Min Act: -0.1700
Data Index: 223608 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0124. Min Act: -0.1700
Data Index: 1038656 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0209. Min Act: -0.1700
Data Index: 1142685 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0124. Min Act: -0.1700
Data Index: 988296 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1299. Min Range: -2.1299
Max Act: 1.9871. Min Act: -0.1700
Data Index: 541226 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1299. Min Range: -2.1299
Max Act: 2.0040. Min Act: -0.1699
Data Index: 624041 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1299. Min Range: -2.1299
Max Act: 1.9956. Min Act: -0.1700
Data Index: 275252 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1299. Min Range: -2.1299
Max Act: 1.9871. Min Act: -0.1700
Data Index: 115107 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1299. Min Range: -2.1299
Max Act: 1.9956. Min Act: -0.1700
Data Index: 384492 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1299. Min Range: -2.1299
Max Act: 1.9956. Min Act: -0.1700
Data Index: 510064 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19