Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 64 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.4083. Min Act: -0.1700
Data Index: 540450 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.2520. Min Act: -0.1700
Data Index: 137975 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.0957. Min Act: -0.1700
Data Index: 1309012 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.1270. Min Act: -0.1700
Data Index: 449241 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.0645. Min Act: -0.1700
Data Index: 1002668 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.0957. Min Act: -0.1700
Data Index: 145059 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.0332. Min Act: -0.1700
Data Index: 1358623 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.0019. Min Act: -0.1700
Data Index: 300122 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.0019. Min Act: -0.1700
Data Index: 343194 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4083. Min Range: -4.4083
Max Act: 4.0019. Min Act: -0.1700
Data Index: 1337473 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.9707. Min Act: -0.1700
Data Index: 71160 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.9707. Min Act: -0.1700
Data Index: 216554 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.9081. Min Act: -0.1700
Data Index: 523184 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.9394. Min Act: -0.1700
Data Index: 752801 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.9081. Min Act: -0.1700
Data Index: 752088 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.8456. Min Act: -0.1700
Data Index: 1294481 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.9081. Min Act: -0.1700
Data Index: 658742 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.8768. Min Act: -0.1700
Data Index: 617705 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.8456. Min Act: -0.1700
Data Index: 85459 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4083. Min Range: -4.4083
Max Act: 3.8456. Min Act: -0.1700
Data Index: 638023 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19