Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1994 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.7399. Min Act: -0.1700
Data Index: 1149088 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.7240. Min Act: -0.1700
Data Index: 921149 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.7080. Min Act: -0.1700
Data Index: 29052 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.7080. Min Act: -0.1700
Data Index: 905675 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6920. Min Act: -0.1700
Data Index: 661341 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6759. Min Act: -0.1700
Data Index: 1137242 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6920. Min Act: -0.1700
Data Index: 1121983 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6920. Min Act: -0.1700
Data Index: 262804 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6920. Min Act: -0.1700
Data Index: 1112102 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6920. Min Act: -0.1700
Data Index: 821870 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6920. Min Act: -0.1700
Data Index: 845210 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6920. Min Act: -0.1700
Data Index: 174553 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6920. Min Act: -0.1700
Data Index: 501439 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.7080. Min Act: -0.1700
Data Index: 1223185 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6599. Min Act: -0.1700
Data Index: 249218 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6759. Min Act: -0.1700
Data Index: 985948 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6759. Min Act: -0.1700
Data Index: 938710 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6920. Min Act: -0.1700
Data Index: 925901 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6759. Min Act: -0.1700
Data Index: 554889 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7399. Min Range: -2.7399
Max Act: 2.6759. Min Act: -0.1700
Data Index: 500361 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19