Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1984 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.7487. Min Act: -0.1700
Data Index: 155543 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6847. Min Act: -0.1700
Data Index: 236910 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.7007. Min Act: -0.1700
Data Index: 797109 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6687. Min Act: -0.1700
Data Index: 927364 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6527. Min Act: -0.1700
Data Index: 40157 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6205. Min Act: -0.1700
Data Index: 394281 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6205. Min Act: -0.1700
Data Index: 231899 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6205. Min Act: -0.1700
Data Index: 616418 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6205. Min Act: -0.1700
Data Index: 419300 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6205. Min Act: -0.1700
Data Index: 613282 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.5884. Min Act: -0.1700
Data Index: 305408 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6045. Min Act: -0.1700
Data Index: 969538 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.6045. Min Act: -0.1700
Data Index: 410585 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.5723. Min Act: -0.1700
Data Index: 393874 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.5884. Min Act: -0.1700
Data Index: 658152 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.5723. Min Act: -0.1700
Data Index: 494896 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.5723. Min Act: -0.1700
Data Index: 1224048 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.5400. Min Act: -0.1700
Data Index: 332718 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.5561. Min Act: -0.1700
Data Index: 138132 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7487. Min Range: -2.7487
Max Act: 2.5400. Min Act: -0.1700
Data Index: 534423 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19