Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 309 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.6873. Min Act: -0.1700
Data Index: 1248426 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.6392. Min Act: -0.1700
Data Index: 611775 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.6553. Min Act: -0.1700
Data Index: 230462 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.6392. Min Act: -0.1700
Data Index: 1353273 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.6392. Min Act: -0.1700
Data Index: 313054 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.6232. Min Act: -0.1700
Data Index: 114919 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.6232. Min Act: -0.1700
Data Index: 441918 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.6071. Min Act: -0.1700
Data Index: 1358366 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.6071. Min Act: -0.1700
Data Index: 313860 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5910. Min Act: -0.1700
Data Index: 538055 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5910. Min Act: -0.1700
Data Index: 802940 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5910. Min Act: -0.1700
Data Index: 293425 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5749. Min Act: -0.1700
Data Index: 731339 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5910. Min Act: -0.1700
Data Index: 1284242 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5910. Min Act: -0.1700
Data Index: 517345 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5749. Min Act: -0.1700
Data Index: 464274 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5910. Min Act: -0.1700
Data Index: 454868 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5749. Min Act: -0.1700
Data Index: 90037 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5588. Min Act: -0.1700
Data Index: 883663 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6873. Min Range: -2.6873
Max Act: 2.5749. Min Act: -0.1700
Data Index: 1077580 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19