Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1484 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.3000. Min Act: -0.1700
Data Index: 800416 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.2219. Min Act: -0.1700
Data Index: 356748 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.1750. Min Act: -0.1700
Data Index: 1121542 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.1594. Min Act: -0.1699
Data Index: 188631 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.1750. Min Act: -0.1700
Data Index: 848837 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.1437. Min Act: -0.1699
Data Index: 341065 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.1437. Min Act: -0.1699
Data Index: 1121714 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.0969. Min Act: -0.1700
Data Index: 73732 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.1437. Min Act: -0.1700
Data Index: 903423 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.1437. Min Act: -0.1700
Data Index: 564776 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.1281. Min Act: -0.1699
Data Index: 1139942 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.1125. Min Act: -0.1699
Data Index: 493462 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.0812. Min Act: -0.1700
Data Index: 896458 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.0812. Min Act: -0.1699
Data Index: 232801 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.0969. Min Act: -0.1700
Data Index: 960110 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.0812. Min Act: -0.1699
Data Index: 261197 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.0812. Min Act: -0.1700
Data Index: 403943 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.0656. Min Act: -0.1700
Data Index: 1129191 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.0656. Min Act: -0.1700
Data Index: 472003 (C4 (Web Text))
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3000. Min Range: -4.3000
Max Act: 4.0343. Min Act: -0.1699
Data Index: 386908 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19