Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 80 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6776. Min Act: -0.1700
Data Index: 653023 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6937. Min Act: -0.1700
Data Index: 922649 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6616. Min Act: -0.1700
Data Index: 1102865 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6616. Min Act: -0.1700
Data Index: 1008837 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6616. Min Act: -0.1700
Data Index: 643461 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6616. Min Act: -0.1700
Data Index: 616734 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6456. Min Act: -0.1700
Data Index: 1297654 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6295. Min Act: -0.1700
Data Index: 731311 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6295. Min Act: -0.1700
Data Index: 576739 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6134. Min Act: -0.1700
Data Index: 632403 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6295. Min Act: -0.1700
Data Index: 278093 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6295. Min Act: -0.1700
Data Index: 599857 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6134. Min Act: -0.1700
Data Index: 1053352 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6134. Min Act: -0.1700
Data Index: 1331192 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.5974. Min Act: -0.1700
Data Index: 357875 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6134. Min Act: -0.1700
Data Index: 1293178 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6295. Min Act: -0.1700
Data Index: 214379 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6134. Min Act: -0.1700
Data Index: 622636 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.6134. Min Act: -0.1700
Data Index: 512864 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6937. Min Range: -2.6937
Max Act: 2.5813. Min Act: -0.1700
Data Index: 295979 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19