Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 15 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.7892. Min Act: -0.1700
Data Index: 754936 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.7267. Min Act: -0.1700
Data Index: 197793 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6642. Min Act: -0.1700
Data Index: 456326 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6642. Min Act: -0.1700
Data Index: 1302040 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6642. Min Act: -0.1700
Data Index: 699345 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6329. Min Act: -0.1700
Data Index: 116760 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6329. Min Act: -0.1700
Data Index: 1043033 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6642. Min Act: -0.1700
Data Index: 974907 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6329. Min Act: -0.1700
Data Index: 1353813 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6017. Min Act: -0.1700
Data Index: 298264 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6017. Min Act: -0.1700
Data Index: 204932 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.6017. Min Act: -0.1700
Data Index: 375603 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.5392. Min Act: -0.1700
Data Index: 566761 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.5079. Min Act: -0.1700
Data Index: 633844 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.5079. Min Act: -0.1700
Data Index: 297445 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.4454. Min Act: -0.1700
Data Index: 1207312 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.4766. Min Act: -0.1700
Data Index: 1010813 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.4766. Min Act: -0.1700
Data Index: 669028 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.4766. Min Act: -0.1700
Data Index: 1100687 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7892. Min Range: -4.7892
Max Act: 4.4454. Min Act: -0.1700
Data Index: 429708 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19