Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 85 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3262. Min Act: -0.1700
Data Index: 414648 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3262. Min Act: -0.1700
Data Index: 1552809 (Python Code)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3262. Min Act: -0.1700
Data Index: 1617592 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3262. Min Act: -0.1700
Data Index: 1605986 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3098. Min Act: -0.1700
Data Index: 1472550 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3098. Min Act: -0.1700
Data Index: 1555149 (Python Code)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3262. Min Act: -0.1699
Data Index: 1557577 (Python Code)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3262. Min Act: -0.1700
Data Index: 1505705 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3262. Min Act: -0.1700
Data Index: 1459872 (Python Code)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3098. Min Act: -0.1700
Data Index: 1637889 (Python Code)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.2934. Min Act: -0.1700
Data Index: 1416543 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.2934. Min Act: -0.1700
Data Index: 1562359 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.2934. Min Act: -0.1700
Data Index: 1554815 (Python Code)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.2934. Min Act: -0.1700
Data Index: 1365107 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.2934. Min Act: -0.1700
Data Index: 1443810 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.2934. Min Act: -0.1700
Data Index: 1531667 (Python Code)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3098. Min Act: -0.1700
Data Index: 1626546 (Python Code)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3098. Min Act: -0.1699
Data Index: 1578727 (Python Code)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.2769. Min Act: -0.1700
Data Index: 1450519 (Python Code)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3262. Min Range: -2.3262
Max Act: 2.3098. Min Act: -0.1700
Data Index: 1573726 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19