Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 955 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.3862. Min Act: -0.1700
Data Index: 1257622 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.1886. Min Act: -0.1700
Data Index: 496177 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.1387. Min Act: -0.1700
Data Index: 966353 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.1220. Min Act: -0.1700
Data Index: 493451 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0886. Min Act: -0.1700
Data Index: 791805 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0886. Min Act: -0.1700
Data Index: 1292318 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0718. Min Act: -0.1700
Data Index: 14239 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0718. Min Act: -0.1700
Data Index: 1072831 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0382. Min Act: -0.1700
Data Index: 666648 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0550. Min Act: -0.1700
Data Index: 984323 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0550. Min Act: -0.1700
Data Index: 1063737 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0382. Min Act: -0.1700
Data Index: 1163776 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0382. Min Act: -0.1700
Data Index: 78139 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0382. Min Act: -0.1700
Data Index: 461762 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0214. Min Act: -0.1700
Data Index: 561752 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0382. Min Act: -0.1700
Data Index: 33343 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0382. Min Act: -0.1700
Data Index: 1079576 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0382. Min Act: -0.1700
Data Index: 352406 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0214. Min Act: -0.1700
Data Index: 1107792 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3862. Min Range: -2.3862
Max Act: 2.0214. Min Act: -0.1700
Data Index: 91539 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19