Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 428 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0314. Min Range: -6.0314
Max Act: 6.0314. Min Act: -0.1700
Data Index: 990503 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0314. Min Range: -6.0314
Max Act: 6.0002. Min Act: -0.1700
Data Index: 1004093 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.8127. Min Act: -0.1700
Data Index: 1062940 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.8127. Min Act: -0.1700
Data Index: 757032 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.7814. Min Act: -0.1700
Data Index: 948895 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.7189. Min Act: -0.1700
Data Index: 753052 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.6877. Min Act: -0.1700
Data Index: 1082743 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.7502. Min Act: -0.1700
Data Index: 265035 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.6877. Min Act: -0.1700
Data Index: 873006 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.7189. Min Act: -0.1700
Data Index: 967509 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.7502. Min Act: -0.1700
Data Index: 893667 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.7502. Min Act: -0.1700
Data Index: 1305146 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.6877. Min Act: -0.1700
Data Index: 908264 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.7189. Min Act: -0.1700
Data Index: 123513 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.6877. Min Act: -0.1700
Data Index: 1191207 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.7189. Min Act: -0.1700
Data Index: 1351097 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.6564. Min Act: -0.1700
Data Index: 916860 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.6564. Min Act: -0.1700
Data Index: 528632 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.6564. Min Act: -0.1700
Data Index: 888294 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0314. Min Range: -6.0314
Max Act: 5.6252. Min Act: -0.1700
Data Index: 1066892 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19