Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2026 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.9203. Min Act: -0.1700
Data Index: 105477 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.9203. Min Act: -0.1700
Data Index: 712377 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.9516. Min Act: -0.1700
Data Index: 366226 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.8891. Min Act: -0.1700
Data Index: 260005 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.9203. Min Act: -0.1700
Data Index: 1137495 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.8578. Min Act: -0.1700
Data Index: 603493 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.8578. Min Act: -0.1700
Data Index: 282770 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7639. Min Act: -0.1700
Data Index: 600260 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.8578. Min Act: -0.1700
Data Index: 519633 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.8265. Min Act: -0.1700
Data Index: 990620 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7639. Min Act: -0.1700
Data Index: 330664 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7639. Min Act: -0.1700
Data Index: 376359 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7326. Min Act: -0.1700
Data Index: 772519 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7639. Min Act: -0.1700
Data Index: 788812 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7326. Min Act: -0.1700
Data Index: 115926 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7326. Min Act: -0.1700
Data Index: 612620 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7639. Min Act: -0.1700
Data Index: 321592 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7639. Min Act: -0.1700
Data Index: 1075649 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7639. Min Act: -0.1700
Data Index: 52243 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9516. Min Range: -3.9516
Max Act: 3.7014. Min Act: -0.1700
Data Index: 1093077 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19