Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1045 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.7944. Min Act: -0.1700
Data Index: 87250 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.7465. Min Act: -0.1700
Data Index: 1205822 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.7305. Min Act: -0.1700
Data Index: 1075173 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6986. Min Act: -0.1699
Data Index: 1380909 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6826. Min Act: -0.1700
Data Index: 1284741 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6986. Min Act: -0.1700
Data Index: 899763 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6986. Min Act: -0.1700
Data Index: 791210 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6826. Min Act: -0.1700
Data Index: 702814 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6986. Min Act: -0.1700
Data Index: 305046 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6826. Min Act: -0.1700
Data Index: 215378 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6665. Min Act: -0.1700
Data Index: 377237 (C4 (Web Text))
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6665. Min Act: -0.1700
Data Index: 461636 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6665. Min Act: -0.1700
Data Index: 446237 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6665. Min Act: -0.1700
Data Index: 190583 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6665. Min Act: -0.1700
Data Index: 1292157 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6505. Min Act: -0.1700
Data Index: 838709 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6505. Min Act: -0.1700
Data Index: 20587 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6344. Min Act: -0.1700
Data Index: 374830 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6505. Min Act: -0.1700
Data Index: 660979 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7944. Min Range: -2.7944
Max Act: 2.6505. Min Act: -0.1700
Data Index: 1190051 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19