Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1195 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.6505. Min Act: -0.1700
Data Index: 463473 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.6344. Min Act: -0.1700
Data Index: 203907 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.6023. Min Act: -0.1700
Data Index: 99717 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.6023. Min Act: -0.1700
Data Index: 1060844 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.6023. Min Act: -0.1700
Data Index: 546043 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.6023. Min Act: -0.1700
Data Index: 681529 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5862. Min Act: -0.1700
Data Index: 667094 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.6023. Min Act: -0.1700
Data Index: 192553 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5701. Min Act: -0.1700
Data Index: 1015635 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5701. Min Act: -0.1700
Data Index: 51925 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5701. Min Act: -0.1700
Data Index: 1299764 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5701. Min Act: -0.1700
Data Index: 1341496 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5701. Min Act: -0.1700
Data Index: 936000 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5701. Min Act: -0.1700
Data Index: 173873 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5701. Min Act: -0.1700
Data Index: 1256545 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5539. Min Act: -0.1700
Data Index: 1038828 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5539. Min Act: -0.1700
Data Index: 1352959 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5539. Min Act: -0.1700
Data Index: 1173288 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5539. Min Act: -0.1700
Data Index: 1197584 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6505. Min Range: -2.6505
Max Act: 2.5539. Min Act: -0.1700
Data Index: 519228 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19