Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1223 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.3614. Min Act: -0.1700
Data Index: 114927 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.3450. Min Act: -0.1700
Data Index: 765124 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.3286. Min Act: -0.1700
Data Index: 547064 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.3122. Min Act: -0.1700
Data Index: 543553 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.3122. Min Act: -0.1700
Data Index: 696984 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.2628. Min Act: -0.1700
Data Index: 116917 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.2463. Min Act: -0.1700
Data Index: 695317 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1966. Min Act: -0.1700
Data Index: 1609342 (Python Code)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.2298. Min Act: -0.1700
Data Index: 302455 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1800. Min Act: -0.1700
Data Index: 719456 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1966. Min Act: -0.1700
Data Index: 1152347 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1966. Min Act: -0.1700
Data Index: 457118 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1966. Min Act: -0.1700
Data Index: 506698 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1634. Min Act: -0.1700
Data Index: 49044 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1634. Min Act: -0.1700
Data Index: 679721 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1634. Min Act: -0.1700
Data Index: 385935 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1468. Min Act: -0.1700
Data Index: 1157262 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1634. Min Act: -0.1700
Data Index: 808532 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1634. Min Act: -0.1700
Data Index: 687561 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3614. Min Range: -2.3614
Max Act: 2.1634. Min Act: -0.1700
Data Index: 293657 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19