Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1595 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.8686. Min Act: -0.1700
Data Index: 118433 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.5874. Min Act: -0.1700
Data Index: 581688 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.6186. Min Act: -0.1700
Data Index: 1231570 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.4936. Min Act: -0.1700
Data Index: 276922 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.6811. Min Act: -0.1700
Data Index: 316603 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.5249. Min Act: -0.1700
Data Index: 862005 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.3998. Min Act: -0.1700
Data Index: 1342366 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.4623. Min Act: -0.1700
Data Index: 876061 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.3686. Min Act: -0.1700
Data Index: 999321 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.4936. Min Act: -0.1700
Data Index: 329018 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.4623. Min Act: -0.1700
Data Index: 1249693 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.4936. Min Act: -0.1700
Data Index: 1280137 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.4623. Min Act: -0.1700
Data Index: 888744 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.5561. Min Act: -0.1700
Data Index: 817247 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.4623. Min Act: -0.1700
Data Index: 1323276 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.4936. Min Act: -0.1700
Data Index: 44917 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.3998. Min Act: -0.1700
Data Index: 556981 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.3686. Min Act: -0.1700
Data Index: 116695 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.4936. Min Act: -0.1700
Data Index: 1093124 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8686. Min Range: -4.8686
Max Act: 4.3061. Min Act: -0.1700
Data Index: 511812 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19