Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 239 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5817. Min Act: -0.1700
Data Index: 37548 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5504. Min Act: -0.1700
Data Index: 1018959 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5347. Min Act: -0.1700
Data Index: 1012106 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5661. Min Act: -0.1700
Data Index: 1254664 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5504. Min Act: -0.1700
Data Index: 1277555 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5504. Min Act: -0.1700
Data Index: 91209 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.4877. Min Act: -0.1700
Data Index: 1301272 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5034. Min Act: -0.1700
Data Index: 977049 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5347. Min Act: -0.1700
Data Index: 912982 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.4877. Min Act: -0.1700
Data Index: 1222962 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5034. Min Act: -0.1700
Data Index: 876200 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.4877. Min Act: -0.1700
Data Index: 595416 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5034. Min Act: -0.1700
Data Index: 519027 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.4721. Min Act: -0.1700
Data Index: 142948 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5347. Min Act: -0.1700
Data Index: 551031 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5191. Min Act: -0.1700
Data Index: 1282257 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.4721. Min Act: -0.1700
Data Index: 274921 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5191. Min Act: -0.1700
Data Index: 454820 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.4877. Min Act: -0.1700
Data Index: 1032509 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5817. Min Range: -3.5817
Max Act: 3.5191. Min Act: -0.1700
Data Index: 571366 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19