Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 328 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.7422. Min Act: -0.1700
Data Index: 411134 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.6942. Min Act: -0.1700
Data Index: 297777 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.6782. Min Act: -0.1700
Data Index: 1113802 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.6301. Min Act: -0.1700
Data Index: 829499 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.6301. Min Act: -0.1700
Data Index: 551874 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.6301. Min Act: -0.1700
Data Index: 349124 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.6301. Min Act: -0.1700
Data Index: 1055429 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.6140. Min Act: -0.1700
Data Index: 1303005 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5979. Min Act: -0.1700
Data Index: 628848 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5979. Min Act: -0.1700
Data Index: 486292 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5818. Min Act: -0.1700
Data Index: 251498 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5979. Min Act: -0.1700
Data Index: 849128 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5818. Min Act: -0.1700
Data Index: 745475 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5818. Min Act: -0.1700
Data Index: 1328712 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5818. Min Act: -0.1700
Data Index: 735882 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5657. Min Act: -0.1700
Data Index: 154587 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5818. Min Act: -0.1700
Data Index: 1066599 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5818. Min Act: -0.1700
Data Index: 616932 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5657. Min Act: -0.1700
Data Index: 1480185 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7422. Min Range: -2.7422
Max Act: 2.5657. Min Act: -0.1700
Data Index: 546473 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19