Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 858 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.8864. Min Act: -0.1700
Data Index: 1261207 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.8551. Min Act: -0.1700
Data Index: 618201 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.8239. Min Act: -0.1700
Data Index: 501224 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.7614. Min Act: -0.1700
Data Index: 1328531 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.6676. Min Act: -0.1700
Data Index: 1436056 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.7301. Min Act: -0.1700
Data Index: 869535 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.5738. Min Act: -0.1700
Data Index: 717515 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.6363. Min Act: -0.1700
Data Index: 1076162 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.5426. Min Act: -0.1700
Data Index: 876732 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.6363. Min Act: -0.1700
Data Index: 1232013 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.6676. Min Act: -0.1700
Data Index: 1105422 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.5426. Min Act: -0.1700
Data Index: 364679 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.4801. Min Act: -0.1700
Data Index: 1182584 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.6363. Min Act: -0.1700
Data Index: 718999 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.4801. Min Act: -0.1700
Data Index: 724020 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.6051. Min Act: -0.1700
Data Index: 1076846 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.5426. Min Act: -0.1700
Data Index: 105153 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.4801. Min Act: -0.1700
Data Index: 1089754 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.5738. Min Act: -0.1700
Data Index: 1084227 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8864. Min Range: -4.8864
Max Act: 4.5113. Min Act: -0.1700
Data Index: 490543 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19