Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 148 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.8054. Min Act: -0.1700
Data Index: 1075769 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.7256. Min Act: -0.1700
Data Index: 1113875 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6616. Min Act: -0.1700
Data Index: 932817 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6776. Min Act: -0.1700
Data Index: 380310 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6616. Min Act: -0.1700
Data Index: 65438 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6616. Min Act: -0.1700
Data Index: 46161 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6456. Min Act: -0.1700
Data Index: 229857 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6456. Min Act: -0.1700
Data Index: 1147126 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6456. Min Act: -0.1700
Data Index: 1349707 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6295. Min Act: -0.1700
Data Index: 1077868 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6295. Min Act: -0.1700
Data Index: 668310 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6295. Min Act: -0.1700
Data Index: 474802 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5973. Min Act: -0.1700
Data Index: 1349454 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6134. Min Act: -0.1700
Data Index: 566502 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6295. Min Act: -0.1700
Data Index: 30808 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6134. Min Act: -0.1700
Data Index: 584497 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5973. Min Act: -0.1700
Data Index: 156192 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.6134. Min Act: -0.1700
Data Index: 401633 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5812. Min Act: -0.1700
Data Index: 1119320 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8054. Min Range: -2.8054
Max Act: 2.5973. Min Act: -0.1700
Data Index: 363060 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19