Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1551 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4533. Min Range: -2.4533
Max Act: 2.4533. Min Act: -0.1700
Data Index: 34057 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.9728. Min Act: -0.1697
Data Index: 740870 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.9728. Min Act: -0.1700
Data Index: 1327836 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.9728. Min Act: -0.1700
Data Index: 1010725 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.9558. Min Act: -0.1700
Data Index: 894473 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.9388. Min Act: -0.1700
Data Index: 1423316 (Python Code)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.9558. Min Act: -0.1700
Data Index: 581574 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.9219. Min Act: -0.1700
Data Index: 365240 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8878. Min Act: -0.1698
Data Index: 1345292 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8707. Min Act: -0.1700
Data Index: 1000836 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8707. Min Act: -0.1700
Data Index: 239849 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8707. Min Act: -0.1700
Data Index: 726374 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8707. Min Act: -0.1700
Data Index: 493586 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8707. Min Act: -0.1700
Data Index: 626469 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8707. Min Act: -0.1700
Data Index: 405712 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8707. Min Act: -0.1616
Data Index: 144784 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8536. Min Act: -0.1699
Data Index: 1236878 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8365. Min Act: -0.1699
Data Index: 1198801 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8279. Min Act: -0.1700
Data Index: 282274 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4533. Min Range: -2.4533
Max Act: 1.8279. Min Act: -0.1700
Data Index: 246292 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19