Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2008 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.3397. Min Act: -0.1700
Data Index: 865301 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.2460. Min Act: -0.1700
Data Index: 1155537 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.2460. Min Act: -0.1700
Data Index: 566005 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.1522. Min Act: -0.1700
Data Index: 836598 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.1522. Min Act: -0.1700
Data Index: 1064440 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.2460. Min Act: -0.1700
Data Index: 554586 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.2147. Min Act: -0.1700
Data Index: 1156511 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.1522. Min Act: -0.1700
Data Index: 165780 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.0741. Min Act: -0.1700
Data Index: 332874 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.0897. Min Act: -0.1700
Data Index: 106193 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.0897. Min Act: -0.1700
Data Index: 400223 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.1053. Min Act: -0.1700
Data Index: 481561 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.0584. Min Act: -0.1700
Data Index: 1073687 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3397. Min Range: -4.3397
Max Act: 3.9959. Min Act: -0.1700
Data Index: 319607 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.0584. Min Act: -0.1700
Data Index: 1095316 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.1209. Min Act: -0.1700
Data Index: 1292155 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3397. Min Range: -4.3397
Max Act: 3.9959. Min Act: -0.1700
Data Index: 142595 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.0584. Min Act: -0.1700
Data Index: 1252196 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3397. Min Range: -4.3397
Max Act: 4.0584. Min Act: -0.1700
Data Index: 881475 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3397. Min Range: -4.3397
Max Act: 3.9959. Min Act: -0.1700
Data Index: 970276 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19