Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 51 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.7670. Min Act: -0.1700
Data Index: 1377087 (Python Code)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.7510. Min Act: -0.1700
Data Index: 1397384 (Python Code)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.7351. Min Act: -0.1700
Data Index: 586726 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.7351. Min Act: -0.1700
Data Index: 1489267 (Python Code)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.7191. Min Act: -0.1700
Data Index: 850639 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.7031. Min Act: -0.1700
Data Index: 207277 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6711. Min Act: -0.1700
Data Index: 1129570 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6390. Min Act: -0.1700
Data Index: 859099 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6550. Min Act: -0.1700
Data Index: 1604384 (Python Code)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6229. Min Act: -0.1700
Data Index: 1434714 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6390. Min Act: -0.1700
Data Index: 95631 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6390. Min Act: -0.1700
Data Index: 681909 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6229. Min Act: -0.1700
Data Index: 1642626 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6229. Min Act: -0.1700
Data Index: 485756 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6068. Min Act: -0.1700
Data Index: 2556 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6229. Min Act: -0.1700
Data Index: 1037908 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6229. Min Act: -0.1700
Data Index: 894675 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6068. Min Act: -0.1700
Data Index: 179882 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.5907. Min Act: -0.1700
Data Index: 306173 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7670. Min Range: -2.7670
Max Act: 2.6068. Min Act: -0.1700
Data Index: 579189 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19