Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 32 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.9935. Min Act: -0.1700
Data Index: 989236 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.9460. Min Act: -0.1700
Data Index: 542900 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.9302. Min Act: -0.1700
Data Index: 535979 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.9302. Min Act: -0.1700
Data Index: 278186 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.9302. Min Act: -0.1700
Data Index: 555725 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.9144. Min Act: -0.1700
Data Index: 81787 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.9144. Min Act: -0.1700
Data Index: 334902 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8826. Min Act: -0.1700
Data Index: 941429 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8985. Min Act: -0.1700
Data Index: 370612 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.9144. Min Act: -0.1700
Data Index: 1058754 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8826. Min Act: -0.1700
Data Index: 1342161 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8826. Min Act: -0.1700
Data Index: 646774 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8826. Min Act: -0.1700
Data Index: 737068 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8826. Min Act: -0.1700
Data Index: 459742 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8826. Min Act: -0.1700
Data Index: 51125 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8826. Min Act: -0.1700
Data Index: 384367 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8826. Min Act: -0.1700
Data Index: 533751 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8668. Min Act: -0.1700
Data Index: 972318 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8668. Min Act: -0.1700
Data Index: 564900 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9935. Min Range: -2.9935
Max Act: 2.8668. Min Act: -0.1700
Data Index: 795917 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19