Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2012 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.2903. Min Act: -0.1700
Data Index: 772038 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.1965. Min Act: -0.1700
Data Index: 25991 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.1809. Min Act: -0.1700
Data Index: 238718 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.1183. Min Act: -0.1700
Data Index: 779258 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.1183. Min Act: -0.1700
Data Index: 482839 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.0871. Min Act: -0.1700
Data Index: 11128 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.1027. Min Act: -0.1700
Data Index: 1048922 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.0871. Min Act: -0.1700
Data Index: 535506 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.0715. Min Act: -0.1700
Data Index: 712659 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.0558. Min Act: -0.1700
Data Index: 1236818 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.0715. Min Act: -0.1700
Data Index: 77143 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.0402. Min Act: -0.1700
Data Index: 348148 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2903. Min Range: -4.2903
Max Act: 4.0402. Min Act: -0.1700
Data Index: 189357 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2903. Min Range: -4.2903
Max Act: 3.9308. Min Act: -0.1700
Data Index: 149671 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2903. Min Range: -4.2903
Max Act: 3.9308. Min Act: -0.1700
Data Index: 1115457 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2903. Min Range: -4.2903
Max Act: 3.9308. Min Act: -0.1700
Data Index: 793400 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2903. Min Range: -4.2903
Max Act: 3.9620. Min Act: -0.1700
Data Index: 452805 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2903. Min Range: -4.2903
Max Act: 3.9464. Min Act: -0.1700
Data Index: 914431 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2903. Min Range: -4.2903
Max Act: 3.9464. Min Act: -0.1700
Data Index: 904644 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2903. Min Range: -4.2903
Max Act: 3.9620. Min Act: -0.1700
Data Index: 374465 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19