Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1926 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.9971. Min Act: -0.1700
Data Index: 612473 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.9971. Min Act: -0.1700
Data Index: 990139 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.9180. Min Act: -0.1700
Data Index: 927128 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.9496. Min Act: -0.1700
Data Index: 534367 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8862. Min Act: -0.1700
Data Index: 196973 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8862. Min Act: -0.1700
Data Index: 1325419 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.9021. Min Act: -0.1700
Data Index: 185865 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8862. Min Act: -0.1700
Data Index: 478964 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.9021. Min Act: -0.1700
Data Index: 539294 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.9021. Min Act: -0.1700
Data Index: 656719 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8862. Min Act: -0.1700
Data Index: 462321 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8704. Min Act: -0.1700
Data Index: 813702 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8862. Min Act: -0.1700
Data Index: 206230 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8704. Min Act: -0.1700
Data Index: 677465 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8545. Min Act: -0.1700
Data Index: 1250552 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8704. Min Act: -0.1700
Data Index: 23297 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8704. Min Act: -0.1700
Data Index: 534146 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8545. Min Act: -0.1700
Data Index: 345297 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8704. Min Act: -0.1700
Data Index: 239939 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9971. Min Range: -2.9971
Max Act: 2.8704. Min Act: -0.1700
Data Index: 624256 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19