Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 21 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9915. Min Act: -0.1700
Data Index: 741407 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9440. Min Act: -0.1700
Data Index: 1204657 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9440. Min Act: -0.1700
Data Index: 335785 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9440. Min Act: -0.1700
Data Index: 369500 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9281. Min Act: -0.1700
Data Index: 626022 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9281. Min Act: -0.1700
Data Index: 1231388 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9123. Min Act: -0.1700
Data Index: 177989 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9281. Min Act: -0.1700
Data Index: 786400 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9281. Min Act: -0.1700
Data Index: 376108 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9281. Min Act: -0.1700
Data Index: 371333 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9123. Min Act: -0.1700
Data Index: 433078 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9123. Min Act: -0.1700
Data Index: 1331621 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.9123. Min Act: -0.1700
Data Index: 1002913 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.8964. Min Act: -0.1700
Data Index: 763589 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.8964. Min Act: -0.1700
Data Index: 239441 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.8964. Min Act: -0.1700
Data Index: 856325 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.8806. Min Act: -0.1700
Data Index: 87329 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.8806. Min Act: -0.1700
Data Index: 233059 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.8806. Min Act: -0.1700
Data Index: 431106 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9915. Min Range: -2.9915
Max Act: 2.8647. Min Act: -0.1700
Data Index: 88305 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19