Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 202 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.9106. Min Act: -0.1700
Data Index: 355846 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.8471. Min Act: -0.1700
Data Index: 1013584 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.8471. Min Act: -0.1700
Data Index: 368203 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.8630. Min Act: -0.1700
Data Index: 447986 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.8312. Min Act: -0.1700
Data Index: 541032 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.8312. Min Act: -0.1700
Data Index: 863964 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.8471. Min Act: -0.1700
Data Index: 961062 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7994. Min Act: -0.1700
Data Index: 1206296 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.8153. Min Act: -0.1700
Data Index: 872134 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7994. Min Act: -0.1700
Data Index: 1315367 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7994. Min Act: -0.1700
Data Index: 1277677 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7516. Min Act: -0.1700
Data Index: 918466 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7516. Min Act: -0.1700
Data Index: 1065679 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7516. Min Act: -0.1700
Data Index: 766920 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7356. Min Act: -0.1700
Data Index: 1170527 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7356. Min Act: -0.1700
Data Index: 1247063 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7196. Min Act: -0.1700
Data Index: 1072580 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7036. Min Act: -0.1700
Data Index: 1263407 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7036. Min Act: -0.1700
Data Index: 943860 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9106. Min Range: -2.9106
Max Act: 2.7356. Min Act: -0.1700
Data Index: 490270 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19