Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1688 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.6976. Min Act: -0.1700
Data Index: 936824 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.6351. Min Act: -0.1700
Data Index: 290768 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.6351. Min Act: -0.1700
Data Index: 673616 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.5414. Min Act: -0.1700
Data Index: 620260 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.5726. Min Act: -0.1700
Data Index: 142009 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.5726. Min Act: -0.1700
Data Index: 579152 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.5101. Min Act: -0.1700
Data Index: 1129329 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.5101. Min Act: -0.1700
Data Index: 1108700 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.5101. Min Act: -0.1700
Data Index: 1081333 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.4476. Min Act: -0.1700
Data Index: 425380 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.4789. Min Act: -0.1700
Data Index: 170997 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.4789. Min Act: -0.1700
Data Index: 668082 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.4476. Min Act: -0.1700
Data Index: 1144130 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.4164. Min Act: -0.1700
Data Index: 936655 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.4476. Min Act: -0.1700
Data Index: 885738 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.4476. Min Act: -0.1700
Data Index: 1024910 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.3851. Min Act: -0.1700
Data Index: 340149 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.4476. Min Act: -0.1700
Data Index: 473433 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.3851. Min Act: -0.1700
Data Index: 415351 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6976. Min Range: -4.6976
Max Act: 4.3851. Min Act: -0.1700
Data Index: 1356464 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19