Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 530 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.9609. Min Act: -0.1700
Data Index: 877021 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.9609. Min Act: -0.1700
Data Index: 132989 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.9609. Min Act: -0.1700
Data Index: 699620 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.9609. Min Act: -0.1700
Data Index: 304185 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.9296. Min Act: -0.1700
Data Index: 3138 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.9296. Min Act: -0.1700
Data Index: 20059 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.9296. Min Act: -0.1700
Data Index: 1026167 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.9296. Min Act: -0.1700
Data Index: 1056694 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.9609. Min Act: -0.1700
Data Index: 711259 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8983. Min Act: -0.1700
Data Index: 408130 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8671. Min Act: -0.1700
Data Index: 507921 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8983. Min Act: -0.1700
Data Index: 752934 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8983. Min Act: -0.1700
Data Index: 364005 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8983. Min Act: -0.1700
Data Index: 156419 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8983. Min Act: -0.1700
Data Index: 223946 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8983. Min Act: -0.1700
Data Index: 1189543 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8983. Min Act: -0.1700
Data Index: 432955 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8983. Min Act: -0.1700
Data Index: 1258647 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8983. Min Act: -0.1700
Data Index: 1101972 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9609. Min Range: -3.9609
Max Act: 3.8671. Min Act: -0.1700
Data Index: 719319 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19