Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 75 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.5347. Min Act: -0.1700
Data Index: 592567 (C4 (Web Text))
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.5347. Min Act: -0.1700
Data Index: 1615780 (Python Code)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.4699. Min Act: -0.1700
Data Index: 232400 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.4375. Min Act: -0.1700
Data Index: 762897 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.4375. Min Act: -0.1700
Data Index: 1144100 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.4049. Min Act: -0.1700
Data Index: 841381 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3886. Min Act: -0.1700
Data Index: 502986 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3886. Min Act: -0.1700
Data Index: 691388 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3559. Min Act: -0.1700
Data Index: 925645 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3886. Min Act: -0.1700
Data Index: 234594 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3559. Min Act: -0.1700
Data Index: 720055 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3559. Min Act: -0.1700
Data Index: 1260560 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3722. Min Act: -0.1700
Data Index: 672410 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3559. Min Act: -0.1700
Data Index: 1185084 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3395. Min Act: -0.1700
Data Index: 921448 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3722. Min Act: -0.1700
Data Index: 1202261 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3559. Min Act: -0.1700
Data Index: 878087 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3559. Min Act: -0.1700
Data Index: 1150064 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3559. Min Act: -0.1700
Data Index: 808941 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5347. Min Range: -2.5347
Max Act: 2.3559. Min Act: -0.1700
Data Index: 269922 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19