Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 874 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.9496. Min Act: -0.1700
Data Index: 348344 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.7933. Min Act: -0.1699
Data Index: 673758 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.6214. Min Act: -0.1700
Data Index: 901217 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.5589. Min Act: -0.1700
Data Index: 265906 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.4964. Min Act: -0.1700
Data Index: 613058 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.5277. Min Act: -0.1700
Data Index: 614068 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.4339. Min Act: -0.1700
Data Index: 1297457 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.4339. Min Act: -0.1700
Data Index: 348241 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.4496. Min Act: -0.1700
Data Index: 461068 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.4183. Min Act: -0.1700
Data Index: 57390 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.3871. Min Act: -0.1700
Data Index: 1114753 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.4027. Min Act: -0.1700
Data Index: 62757 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.4027. Min Act: -0.1700
Data Index: 852021 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.4027. Min Act: -0.1700
Data Index: 538595 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.4027. Min Act: -0.1700
Data Index: 993930 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.3714. Min Act: -0.1700
Data Index: 248947 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.3558. Min Act: -0.1700
Data Index: 646468 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.3089. Min Act: -0.1700
Data Index: 1286977 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.3558. Min Act: -0.1700
Data Index: 828280 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9496. Min Range: -4.9496
Max Act: 4.2933. Min Act: -0.1700
Data Index: 887233 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19