Model: GELU Model: 1 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1885 in Layer 0
Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')
Click the toggle to see the full text!
Text #0
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.2018. Min Act: -0.1700
Data Index: 143364 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.1721. Min Act: -0.1700
Data Index: 997010 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.1605. Min Act: -0.1700
Data Index: 476588 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.1542. Min Act: -0.1700
Data Index: 980513 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.1399. Min Act: -0.1700
Data Index: 60556 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.1096. Min Act: -0.1700
Data Index: 167931 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.1167. Min Act: -0.1700
Data Index: 171212 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.1229. Min Act: -0.1700
Data Index: 940376 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0894. Min Act: -0.1700
Data Index: 1354305 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0806. Min Act: -0.1700
Data Index: 889656 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0826. Min Act: -0.1700
Data Index: 501694 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0839. Min Act: -0.1700
Data Index: 677388 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0826. Min Act: -0.1700
Data Index: 311885 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0856. Min Act: -0.1700
Data Index: 305457 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0629. Min Act: -0.1700
Data Index: 1302137 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0630. Min Act: -0.1700
Data Index: 362284 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0555. Min Act: -0.1700
Data Index: 530966 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0597. Min Act: -0.1700
Data Index: 362465 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0473. Min Act: -0.1700
Data Index: 581737 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.2018. Min Range: -3.2018
Max Act: 3.0517. Min Act: -0.1700
Data Index: 472391 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full textTruncated
Full Text #19