Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 913 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.7369. Min Act: -0.1700
Data Index: 576816 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6569. Min Act: -0.1700
Data Index: 1012598 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6729. Min Act: -0.1700
Data Index: 1328680 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6729. Min Act: -0.1700
Data Index: 1096141 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6087. Min Act: -0.1700
Data Index: 1115249 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6248. Min Act: -0.1700
Data Index: 118885 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6087. Min Act: -0.1700
Data Index: 262907 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5926. Min Act: -0.1700
Data Index: 1017673 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.6248. Min Act: -0.1700
Data Index: 1214849 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5926. Min Act: -0.1700
Data Index: 822163 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5926. Min Act: -0.1700
Data Index: 70354 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5765. Min Act: -0.1700
Data Index: 760427 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5765. Min Act: -0.1700
Data Index: 686675 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5765. Min Act: -0.1700
Data Index: 554728 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5604. Min Act: -0.1700
Data Index: 665172 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5604. Min Act: -0.1700
Data Index: 274407 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5604. Min Act: -0.1700
Data Index: 139594 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5604. Min Act: -0.1700
Data Index: 86803 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5604. Min Act: -0.1700
Data Index: 88502 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7369. Min Range: -2.7369
Max Act: 2.5765. Min Act: -0.1700
Data Index: 755156 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19