Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2003 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.4339. Min Act: -0.1700
Data Index: 187642 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.4177. Min Act: -0.1700
Data Index: 428475 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.4339. Min Act: -0.1700
Data Index: 1153803 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.4014. Min Act: -0.1700
Data Index: 1144074 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.4177. Min Act: -0.1700
Data Index: 771992 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3850. Min Act: -0.1700
Data Index: 1202728 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3850. Min Act: -0.1700
Data Index: 1335654 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.4014. Min Act: -0.1700
Data Index: 544555 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3687. Min Act: -0.1700
Data Index: 1111042 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3687. Min Act: -0.1700
Data Index: 46070 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3523. Min Act: -0.1700
Data Index: 1133420 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3523. Min Act: -0.1700
Data Index: 1272346 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3523. Min Act: -0.1700
Data Index: 625799 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3359. Min Act: -0.1700
Data Index: 1106856 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3359. Min Act: -0.1700
Data Index: 911324 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3359. Min Act: -0.1700
Data Index: 496945 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3359. Min Act: -0.1700
Data Index: 1073084 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3195. Min Act: -0.1700
Data Index: 347827 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3523. Min Act: -0.1700
Data Index: 678035 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4339. Min Range: -2.4339
Max Act: 2.3195. Min Act: -0.1700
Data Index: 1163511 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19