Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1895 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.2334. Min Act: -0.1700
Data Index: 226812 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.2334. Min Act: -0.1700
Data Index: 608119 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.2003. Min Act: -0.1700
Data Index: 934661 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.2003. Min Act: -0.1700
Data Index: 93451 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1837. Min Act: -0.1700
Data Index: 1184500 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1671. Min Act: -0.1700
Data Index: 99400 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1504. Min Act: -0.1699
Data Index: 820627 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1504. Min Act: -0.1700
Data Index: 759568 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1504. Min Act: -0.1700
Data Index: 103569 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1504. Min Act: -0.1700
Data Index: 649224 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1671. Min Act: -0.1700
Data Index: 846929 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1338. Min Act: -0.1700
Data Index: 71789 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1338. Min Act: -0.1700
Data Index: 352284 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1338. Min Act: -0.1700
Data Index: 109876 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1504. Min Act: -0.1700
Data Index: 586238 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1171. Min Act: -0.1700
Data Index: 200145 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1338. Min Act: -0.1700
Data Index: 1049450 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1171. Min Act: -0.1700
Data Index: 21798 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1004. Min Act: -0.1700
Data Index: 605503 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2334. Min Range: -2.2334
Max Act: 2.1171. Min Act: -0.1700
Data Index: 73154 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19