Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1851 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.9136. Min Act: -0.1700
Data Index: 1150041 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.2852. Min Act: -0.1700
Data Index: 209193 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.2687. Min Act: -0.1699
Data Index: 1243617 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.2357. Min Act: -0.1697
Data Index: 832869 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.2357. Min Act: -0.1699
Data Index: 685779 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.2026. Min Act: -0.1700
Data Index: 1167943 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1860. Min Act: -0.1700
Data Index: 1347490 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1693. Min Act: -0.1700
Data Index: 26372 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1860. Min Act: -0.1700
Data Index: 797340 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1527. Min Act: -0.1699
Data Index: 872540 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1860. Min Act: -0.1700
Data Index: 529685 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1693. Min Act: -0.1663
Data Index: 157494 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1527. Min Act: -0.1700
Data Index: 724461 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1360. Min Act: -0.1700
Data Index: 991576 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1527. Min Act: -0.1692
Data Index: 817546 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1360. Min Act: -0.1663
Data Index: 1144317 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1527. Min Act: -0.1700
Data Index: 1091459 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1527. Min Act: -0.1700
Data Index: 1223387 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1360. Min Act: -0.1700
Data Index: 371248 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9136. Min Range: -2.9136
Max Act: 2.1360. Min Act: -0.1700
Data Index: 487042 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19