Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1579 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.4224. Min Act: -0.1700
Data Index: 139951 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.3287. Min Act: -0.1700
Data Index: 688828 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.3287. Min Act: -0.1700
Data Index: 469879 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.3599. Min Act: -0.1700
Data Index: 708610 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.4224. Min Act: -0.1700
Data Index: 467624 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.2036. Min Act: -0.1700
Data Index: 293323 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.2974. Min Act: -0.1700
Data Index: 7819 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.2036. Min Act: -0.1700
Data Index: 373281 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.2349. Min Act: -0.1700
Data Index: 1003976 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.2662. Min Act: -0.1700
Data Index: 681739 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.2349. Min Act: -0.1700
Data Index: 161585 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.2349. Min Act: -0.1700
Data Index: 839936 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.2349. Min Act: -0.1700
Data Index: 666790 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.1724. Min Act: -0.1700
Data Index: 987250 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.1411. Min Act: -0.1700
Data Index: 1053376 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.1724. Min Act: -0.1700
Data Index: 316349 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.1724. Min Act: -0.1700
Data Index: 1076766 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.1724. Min Act: -0.1700
Data Index: 414760 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.1411. Min Act: -0.1700
Data Index: 542812 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4224. Min Range: -4.4224
Max Act: 4.1411. Min Act: -0.1700
Data Index: 824939 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19