Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1494 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.7486. Min Act: -0.1700
Data Index: 76868 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.5143. Min Act: -0.1700
Data Index: 243701 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.4986. Min Act: -0.1700
Data Index: 812685 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.4518. Min Act: -0.1700
Data Index: 515460 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.4205. Min Act: -0.1700
Data Index: 998850 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.3736. Min Act: -0.1700
Data Index: 821751 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.3267. Min Act: -0.1700
Data Index: 1218727 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2330. Min Act: -0.1700
Data Index: 152236 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2330. Min Act: -0.1700
Data Index: 909119 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2642. Min Act: -0.1700
Data Index: 921164 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2017. Min Act: -0.1700
Data Index: 484109 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2486. Min Act: -0.1700
Data Index: 297294 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2330. Min Act: -0.1700
Data Index: 195590 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2486. Min Act: -0.1700
Data Index: 40891 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2173. Min Act: -0.1700
Data Index: 819595 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.1548. Min Act: -0.1700
Data Index: 1308945 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.1705. Min Act: -0.1700
Data Index: 102431 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2173. Min Act: -0.1700
Data Index: 434195 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.2173. Min Act: -0.1700
Data Index: 1240609 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7486. Min Range: -4.7486
Max Act: 4.1548. Min Act: -0.1700
Data Index: 92643 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19