Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1982 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.8639. Min Act: -0.1700
Data Index: 1648119 (Python Code)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.8003. Min Act: -0.1700
Data Index: 330980 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.7365. Min Act: -0.1700
Data Index: 619188 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.7365. Min Act: -0.1700
Data Index: 320560 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.7365. Min Act: -0.1700
Data Index: 466200 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.7045. Min Act: -0.1700
Data Index: 699795 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.7045. Min Act: -0.1700
Data Index: 1124612 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6885. Min Act: -0.1700
Data Index: 1278514 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6885. Min Act: -0.1700
Data Index: 951150 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6885. Min Act: -0.1700
Data Index: 772886 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6885. Min Act: -0.1700
Data Index: 869603 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6725. Min Act: -0.1700
Data Index: 62935 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6725. Min Act: -0.1700
Data Index: 172916 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6725. Min Act: -0.1700
Data Index: 1321103 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6565. Min Act: -0.1700
Data Index: 1080742 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6565. Min Act: -0.1700
Data Index: 19076 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6404. Min Act: -0.1700
Data Index: 1496696 (Python Code)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6565. Min Act: -0.1700
Data Index: 86685 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6244. Min Act: -0.1700
Data Index: 1290421 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8639. Min Range: -2.8639
Max Act: 2.6244. Min Act: -0.1700
Data Index: 1130579 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19