Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 428 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.6671. Min Act: -0.1700
Data Index: 154818 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.6189. Min Act: -0.1700
Data Index: 1163805 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5867. Min Act: -0.1700
Data Index: 745538 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.6028. Min Act: -0.1700
Data Index: 723074 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.6189. Min Act: -0.1700
Data Index: 1195611 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5706. Min Act: -0.1700
Data Index: 1607686 (Python Code)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5706. Min Act: -0.1700
Data Index: 1646039 (Python Code)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5706. Min Act: -0.1700
Data Index: 1461288 (Python Code)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5867. Min Act: -0.1700
Data Index: 431434 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5706. Min Act: -0.1700
Data Index: 1238144 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5706. Min Act: -0.1700
Data Index: 1216554 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5545. Min Act: -0.1700
Data Index: 1309421 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5545. Min Act: -0.1700
Data Index: 1387668 (Python Code)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5545. Min Act: -0.1700
Data Index: 1598463 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5383. Min Act: -0.1700
Data Index: 1596296 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5383. Min Act: -0.1700
Data Index: 454730 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5222. Min Act: -0.1700
Data Index: 1365941 (Python Code)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5383. Min Act: -0.1700
Data Index: 1406128 (Python Code)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5383. Min Act: -0.1700
Data Index: 1610034 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6671. Min Range: -2.6671
Max Act: 2.5222. Min Act: -0.1700
Data Index: 1509640 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19