Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 84 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0894. Min Range: -3.0894
Max Act: 3.0894. Min Act: -0.1700
Data Index: 251237 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0894. Min Range: -3.0894
Max Act: 3.0894. Min Act: -0.1700
Data Index: 480528 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0894. Min Range: -3.0894
Max Act: 3.0420. Min Act: -0.1700
Data Index: 1531186 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0894. Min Range: -3.0894
Max Act: 3.0104. Min Act: -0.1700
Data Index: 1437183 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.9630. Min Act: -0.1700
Data Index: 1458148 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.9313. Min Act: -0.1700
Data Index: 1551386 (Python Code)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8520. Min Act: -0.1700
Data Index: 1610971 (Python Code)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8837. Min Act: -0.1700
Data Index: 1261289 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8837. Min Act: -0.1700
Data Index: 448000 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8679. Min Act: -0.1700
Data Index: 693812 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8679. Min Act: -0.1700
Data Index: 865161 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8679. Min Act: -0.1700
Data Index: 638517 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8679. Min Act: -0.1700
Data Index: 200920 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8679. Min Act: -0.1700
Data Index: 196173 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8520. Min Act: -0.1700
Data Index: 1540849 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8361. Min Act: -0.1700
Data Index: 1363928 (Python Code)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8361. Min Act: -0.1700
Data Index: 1070124 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8361. Min Act: -0.1700
Data Index: 881113 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8679. Min Act: -0.1700
Data Index: 538218 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0894. Min Range: -3.0894
Max Act: 2.8361. Min Act: -0.1700
Data Index: 1562475 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19