Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1855 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1427. Min Range: -3.1427
Max Act: 3.1427. Min Act: -0.1700
Data Index: 883916 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1427. Min Range: -3.1427
Max Act: 3.1112. Min Act: -0.1700
Data Index: 365517 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1427. Min Range: -3.1427
Max Act: 3.0639. Min Act: -0.1700
Data Index: 1253121 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1427. Min Range: -3.1427
Max Act: 3.0165. Min Act: -0.1700
Data Index: 30110 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1427. Min Range: -3.1427
Max Act: 3.0007. Min Act: -0.1700
Data Index: 416836 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1427. Min Range: -3.1427
Max Act: 3.0165. Min Act: -0.1700
Data Index: 1242371 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9849. Min Act: -0.1700
Data Index: 1261848 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1427. Min Range: -3.1427
Max Act: 3.0007. Min Act: -0.1700
Data Index: 430001 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9691. Min Act: -0.1700
Data Index: 162377 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9691. Min Act: -0.1700
Data Index: 206299 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9849. Min Act: -0.1700
Data Index: 814007 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9533. Min Act: -0.1700
Data Index: 1175180 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9691. Min Act: -0.1700
Data Index: 770257 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9216. Min Act: -0.1700
Data Index: 646336 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9374. Min Act: -0.1700
Data Index: 694240 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9216. Min Act: -0.1700
Data Index: 309372 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9374. Min Act: -0.1700
Data Index: 811886 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9533. Min Act: -0.1700
Data Index: 198112 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9374. Min Act: -0.1700
Data Index: 896920 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1427. Min Range: -3.1427
Max Act: 2.9216. Min Act: -0.1700
Data Index: 700663 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19