Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1398 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.5281. Min Act: -0.1700
Data Index: 18628 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.4968. Min Act: -0.1700
Data Index: 288083 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.4968. Min Act: -0.1700
Data Index: 62753 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.4341. Min Act: -0.1700
Data Index: 1338248 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.4184. Min Act: -0.1700
Data Index: 255116 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.4184. Min Act: -0.1700
Data Index: 1199162 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3714. Min Act: -0.1700
Data Index: 579306 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3714. Min Act: -0.1700
Data Index: 461331 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3557. Min Act: -0.1700
Data Index: 1032221 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3557. Min Act: -0.1700
Data Index: 16104 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3557. Min Act: -0.1700
Data Index: 593911 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3400. Min Act: -0.1700
Data Index: 1286598 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3557. Min Act: -0.1700
Data Index: 919609 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3557. Min Act: -0.1700
Data Index: 1058475 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3400. Min Act: -0.1700
Data Index: 1145754 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3243. Min Act: -0.1700
Data Index: 761509 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3243. Min Act: -0.1700
Data Index: 271308 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3243. Min Act: -0.1700
Data Index: 564556 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3243. Min Act: -0.1700
Data Index: 1115954 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5281. Min Range: -3.5281
Max Act: 3.3557. Min Act: -0.1700
Data Index: 137325 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19