Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1933 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.4404. Min Act: -0.1700
Data Index: 1275704 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.4078. Min Act: -0.1700
Data Index: 505453 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.3915. Min Act: -0.1700
Data Index: 757048 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.3588. Min Act: -0.1700
Data Index: 770403 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.3752. Min Act: -0.1700
Data Index: 237273 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.3588. Min Act: -0.1700
Data Index: 992285 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.3424. Min Act: -0.1700
Data Index: 1168863 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.2932. Min Act: -0.1696
Data Index: 1554340 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.3096. Min Act: -0.1700
Data Index: 37373 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.3260. Min Act: -0.1700
Data Index: 971822 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.3260. Min Act: -0.1700
Data Index: 319907 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.3096. Min Act: -0.1700
Data Index: 333151 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.2767. Min Act: -0.1700
Data Index: 57874 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.2932. Min Act: -0.1700
Data Index: 918473 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.2932. Min Act: -0.1700
Data Index: 1272094 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.2932. Min Act: -0.1700
Data Index: 280725 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.2932. Min Act: -0.1700
Data Index: 190810 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.2767. Min Act: -0.1700
Data Index: 191070 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.2767. Min Act: -0.1700
Data Index: 876529 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4404. Min Range: -2.4404
Max Act: 2.2767. Min Act: -0.1700
Data Index: 666278 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19