Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1004 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.9788. Min Act: -0.1700
Data Index: 740902 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8837. Min Act: -0.1700
Data Index: 346023 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8837. Min Act: -0.1700
Data Index: 368874 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8519. Min Act: -0.1700
Data Index: 314035 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8361. Min Act: -0.1700
Data Index: 1323691 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8201. Min Act: -0.1700
Data Index: 640184 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8201. Min Act: -0.1700
Data Index: 732873 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8201. Min Act: -0.1700
Data Index: 1354800 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8201. Min Act: -0.1700
Data Index: 270226 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8042. Min Act: -0.1700
Data Index: 871963 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8042. Min Act: -0.1700
Data Index: 1594839 (Python Code)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8042. Min Act: -0.1700
Data Index: 603299 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.7883. Min Act: -0.1700
Data Index: 821800 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8201. Min Act: -0.1700
Data Index: 328397 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8361. Min Act: -0.1700
Data Index: 160666 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8042. Min Act: -0.1700
Data Index: 1266447 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8042. Min Act: -0.1700
Data Index: 1018007 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8201. Min Act: -0.1700
Data Index: 312974 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8042. Min Act: -0.1700
Data Index: 410563 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9788. Min Range: -2.9788
Max Act: 2.8042. Min Act: -0.1700
Data Index: 972480 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19