Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2028 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.3359. Min Range: -5.3359
Max Act: 5.3359. Min Act: -0.1700
Data Index: 130819 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3359. Min Range: -5.3359
Max Act: 5.1796. Min Act: -0.1700
Data Index: 444099 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3359. Min Range: -5.3359
Max Act: 5.1484. Min Act: -0.1700
Data Index: 840499 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3359. Min Range: -5.3359
Max Act: 5.1171. Min Act: -0.1700
Data Index: 379061 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3359. Min Range: -5.3359
Max Act: 5.0546. Min Act: -0.1700
Data Index: 807821 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3359. Min Range: -5.3359
Max Act: 5.0546. Min Act: -0.1700
Data Index: 748340 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3359. Min Range: -5.3359
Max Act: 5.0234. Min Act: -0.1700
Data Index: 1191661 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.9609. Min Act: -0.1700
Data Index: 817873 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.9609. Min Act: -0.1700
Data Index: 772878 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.9296. Min Act: -0.1700
Data Index: 1031607 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.9296. Min Act: -0.1700
Data Index: 96420 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.8984. Min Act: -0.1700
Data Index: 173773 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.9609. Min Act: -0.1700
Data Index: 375691 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.8984. Min Act: -0.1700
Data Index: 1249536 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.9296. Min Act: -0.1700
Data Index: 577205 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.8671. Min Act: -0.1700
Data Index: 284426 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.8984. Min Act: -0.1700
Data Index: 729816 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.8671. Min Act: -0.1700
Data Index: 160922 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.8359. Min Act: -0.1700
Data Index: 396219 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3359. Min Range: -5.3359
Max Act: 4.8671. Min Act: -0.1700
Data Index: 302444 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19