Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1816 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2266. Min Range: -4.2266
Max Act: 4.2266. Min Act: -0.1700
Data Index: 524503 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2266. Min Range: -4.2266
Max Act: 4.1641. Min Act: -0.1700
Data Index: 816216 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2266. Min Range: -4.2266
Max Act: 4.1953. Min Act: -0.1700
Data Index: 1268115 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2266. Min Range: -4.2266
Max Act: 4.1641. Min Act: -0.1700
Data Index: 38863 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.8827. Min Act: -0.1700
Data Index: 297203 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2266. Min Range: -4.2266
Max Act: 4.0390. Min Act: -0.1700
Data Index: 771475 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.9765. Min Act: -0.1700
Data Index: 1312265 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.8827. Min Act: -0.1700
Data Index: 700231 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.8201. Min Act: -0.1700
Data Index: 100926 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.7576. Min Act: -0.1700
Data Index: 315507 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.8827. Min Act: -0.1700
Data Index: 179545 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.7889. Min Act: -0.1700
Data Index: 758043 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.9140. Min Act: -0.1700
Data Index: 215518 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.8201. Min Act: -0.1700
Data Index: 1004573 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.7576. Min Act: -0.1700
Data Index: 416575 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.8827. Min Act: -0.1700
Data Index: 90730 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.8201. Min Act: -0.1700
Data Index: 976554 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.7889. Min Act: -0.1700
Data Index: 3625 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.7889. Min Act: -0.1700
Data Index: 278688 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2266. Min Range: -4.2266
Max Act: 3.7576. Min Act: -0.1700
Data Index: 1015392 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19