Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2009 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.3612. Min Act: -0.1700
Data Index: 261221 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.2987. Min Act: -0.1700
Data Index: 436960 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.2987. Min Act: -0.1700
Data Index: 353704 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.3299. Min Act: -0.1700
Data Index: 1057659 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.2049. Min Act: -0.1700
Data Index: 1096930 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.2362. Min Act: -0.1700
Data Index: 252959 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.1737. Min Act: -0.1700
Data Index: 1046340 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.0799. Min Act: -0.1700
Data Index: 885065 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.0174. Min Act: -0.1700
Data Index: 1142184 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.0174. Min Act: -0.1700
Data Index: 561425 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3612. Min Range: -6.3612
Max Act: 5.9862. Min Act: -0.1700
Data Index: 1020726 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.0799. Min Act: -0.1700
Data Index: 421049 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3612. Min Range: -6.3612
Max Act: 5.9862. Min Act: -0.1700
Data Index: 639631 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3612. Min Range: -6.3612
Max Act: 5.9549. Min Act: -0.1700
Data Index: 663510 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3612. Min Range: -6.3612
Max Act: 6.0799. Min Act: -0.1700
Data Index: 918243 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3612. Min Range: -6.3612
Max Act: 5.9549. Min Act: -0.1700
Data Index: 1026772 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3612. Min Range: -6.3612
Max Act: 5.9549. Min Act: -0.1700
Data Index: 1309080 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3612. Min Range: -6.3612
Max Act: 5.9549. Min Act: -0.1700
Data Index: 1216755 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3612. Min Range: -6.3612
Max Act: 5.9237. Min Act: -0.1700
Data Index: 124333 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3612. Min Range: -6.3612
Max Act: 5.9237. Min Act: -0.1700
Data Index: 541228 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19