Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1043 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.5278. Min Act: -0.1700
Data Index: 736314 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.4653. Min Act: -0.1700
Data Index: 1232373 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.3403. Min Act: -0.1700
Data Index: 1065 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.2778. Min Act: -0.1700
Data Index: 14161 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.1528. Min Act: -0.1700
Data Index: 1209646 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.2153. Min Act: -0.1700
Data Index: 190465 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.1528. Min Act: -0.1700
Data Index: 759497 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.1528. Min Act: -0.1700
Data Index: 1101784 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.2153. Min Act: -0.1700
Data Index: 1253771 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.1528. Min Act: -0.1700
Data Index: 134805 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.1528. Min Act: -0.1700
Data Index: 442346 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.0903. Min Act: -0.1700
Data Index: 711243 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.0903. Min Act: -0.1699
Data Index: 139899 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.0278. Min Act: -0.1700
Data Index: 187591 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.0278. Min Act: -0.1700
Data Index: 102922 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.0278. Min Act: -0.1700
Data Index: 909039 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.0278. Min Act: -0.1700
Data Index: 854869 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5278. Min Range: -9.5278
Max Act: 9.0903. Min Act: -0.1699
Data Index: 1264056 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5278. Min Range: -9.5278
Max Act: 8.9653. Min Act: -0.1700
Data Index: 1216826 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5278. Min Range: -9.5278
Max Act: 8.9028. Min Act: -0.1700
Data Index: 1056778 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19