Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1795 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.5441. Min Act: -0.1700
Data Index: 510308 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4956. Min Act: -0.1700
Data Index: 884193 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4794. Min Act: -0.1700
Data Index: 1212344 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4794. Min Act: -0.1700
Data Index: 1084872 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4794. Min Act: -0.1700
Data Index: 1124937 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4794. Min Act: -0.1700
Data Index: 908400 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4632. Min Act: -0.1700
Data Index: 1345617 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4469. Min Act: -0.1700
Data Index: 708344 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4469. Min Act: -0.1700
Data Index: 939249 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4632. Min Act: -0.1700
Data Index: 749152 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4469. Min Act: -0.1700
Data Index: 1214783 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4469. Min Act: -0.1700
Data Index: 336938 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4469. Min Act: -0.1700
Data Index: 84509 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4307. Min Act: -0.1700
Data Index: 1111294 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4307. Min Act: -0.1700
Data Index: 646299 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4307. Min Act: -0.1700
Data Index: 94750 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4307. Min Act: -0.1700
Data Index: 823505 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4307. Min Act: -0.1700
Data Index: 77728 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4307. Min Act: -0.1700
Data Index: 1427116 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5441. Min Range: -2.5441
Max Act: 2.4144. Min Act: -0.1700
Data Index: 1381607 (Python Code)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19