Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1393 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0693. Min Range: -3.0693
Max Act: 3.0693. Min Act: -0.1700
Data Index: 1004977 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0693. Min Range: -3.0693
Max Act: 3.0220. Min Act: -0.1700
Data Index: 209941 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0693. Min Range: -3.0693
Max Act: 3.0062. Min Act: -0.1700
Data Index: 1288918 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0693. Min Range: -3.0693
Max Act: 3.0062. Min Act: -0.1700
Data Index: 2286 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9745. Min Act: -0.1700
Data Index: 754978 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9745. Min Act: -0.1700
Data Index: 676410 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9745. Min Act: -0.1700
Data Index: 1059308 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9587. Min Act: -0.1700
Data Index: 1309054 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9587. Min Act: -0.1700
Data Index: 897452 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9587. Min Act: -0.1700
Data Index: 862005 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9429. Min Act: -0.1700
Data Index: 325723 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9270. Min Act: -0.1700
Data Index: 787715 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9270. Min Act: -0.1700
Data Index: 1082373 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9112. Min Act: -0.1700
Data Index: 1111342 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9270. Min Act: -0.1700
Data Index: 574379 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9112. Min Act: -0.1700
Data Index: 631121 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9112. Min Act: -0.1700
Data Index: 507165 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9112. Min Act: -0.1700
Data Index: 968563 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9112. Min Act: -0.1700
Data Index: 47288 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0693. Min Range: -3.0693
Max Act: 2.9112. Min Act: -0.1700
Data Index: 438188 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19