Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1958 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.8059. Min Act: -0.1700
Data Index: 333344 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.6496. Min Act: -0.1700
Data Index: 300628 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.6496. Min Act: -0.1700
Data Index: 1101682 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.6496. Min Act: -0.1700
Data Index: 578273 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.5559. Min Act: -0.1700
Data Index: 527747 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.4934. Min Act: -0.1700
Data Index: 259818 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.4621. Min Act: -0.1700
Data Index: 847646 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3996. Min Act: -0.1699
Data Index: 1057201 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.4621. Min Act: -0.1700
Data Index: 731619 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.4308. Min Act: -0.1700
Data Index: 221797 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.4308. Min Act: -0.1700
Data Index: 1254150 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3996. Min Act: -0.1700
Data Index: 1013156 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3996. Min Act: -0.1700
Data Index: 588522 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3371. Min Act: -0.1700
Data Index: 48768 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3996. Min Act: -0.1700
Data Index: 1181434 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3371. Min Act: -0.1700
Data Index: 263403 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3683. Min Act: -0.1700
Data Index: 1133853 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3683. Min Act: -0.1700
Data Index: 83464 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3683. Min Act: -0.1700
Data Index: 722870 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8059. Min Range: -4.8059
Max Act: 4.3058. Min Act: -0.1700
Data Index: 230857 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19