Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1270 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.6482. Min Act: -0.1700
Data Index: 1092343 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.6161. Min Act: -0.1700
Data Index: 1041114 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5839. Min Act: -0.1699
Data Index: 847092 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.6161. Min Act: -0.1700
Data Index: 932144 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.6000. Min Act: -0.1700
Data Index: 1440383 (Python Code)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5678. Min Act: -0.1700
Data Index: 648120 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.6000. Min Act: -0.1700
Data Index: 412378 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5678. Min Act: -0.1700
Data Index: 1196267 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5678. Min Act: -0.1700
Data Index: 376027 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5839. Min Act: -0.1700
Data Index: 59209 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5517. Min Act: -0.1700
Data Index: 1217117 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5678. Min Act: -0.1700
Data Index: 1131957 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5678. Min Act: -0.1699
Data Index: 582374 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5678. Min Act: -0.1700
Data Index: 1312007 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5678. Min Act: -0.1700
Data Index: 1558538 (Python Code)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5355. Min Act: -0.1700
Data Index: 1228359 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5355. Min Act: -0.1700
Data Index: 49243 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5678. Min Act: -0.1692
Data Index: 1336842 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5355. Min Act: -0.1700
Data Index: 1078378 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6482. Min Range: -2.6482
Max Act: 2.5194. Min Act: -0.1700
Data Index: 1237742 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19