Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.7305. Min Act: -0.1700
Data Index: 373995 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.6055. Min Act: -0.1700
Data Index: 392198 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.5430. Min Act: -0.1700
Data Index: 185038 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.4180. Min Act: -0.1700
Data Index: 220196 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.3867. Min Act: -0.1700
Data Index: 635380 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.3867. Min Act: -0.1700
Data Index: 744594 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.3242. Min Act: -0.1700
Data Index: 581477 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.3867. Min Act: -0.1700
Data Index: 1330716 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.3555. Min Act: -0.1700
Data Index: 962903 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.3555. Min Act: -0.1700
Data Index: 9174 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.3242. Min Act: -0.1700
Data Index: 1206837 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.2930. Min Act: -0.1700
Data Index: 388794 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.2617. Min Act: -0.1700
Data Index: 850914 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.2930. Min Act: -0.1700
Data Index: 1163708 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.2617. Min Act: -0.1700
Data Index: 492661 (C4 (Web Text))
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.2617. Min Act: -0.1700
Data Index: 738777 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.2617. Min Act: -0.1700
Data Index: 1271344 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.2617. Min Act: -0.1700
Data Index: 791166 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.2930. Min Act: -0.1700
Data Index: 1174493 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7305. Min Range: -4.7305
Max Act: 4.2617. Min Act: -0.1700
Data Index: 902901 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19