Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2021 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.8048. Min Act: -0.1700
Data Index: 720616 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.7730. Min Act: -0.1700
Data Index: 1191971 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.7251. Min Act: -0.1700
Data Index: 873990 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.7091. Min Act: -0.1700
Data Index: 746349 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6931. Min Act: -0.1700
Data Index: 448572 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6771. Min Act: -0.1700
Data Index: 401214 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6610. Min Act: -0.1700
Data Index: 355712 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6610. Min Act: -0.1700
Data Index: 697961 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6450. Min Act: -0.1700
Data Index: 989429 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6289. Min Act: -0.1700
Data Index: 626594 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6129. Min Act: -0.1700
Data Index: 190136 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6129. Min Act: -0.1700
Data Index: 325307 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6129. Min Act: -0.1700
Data Index: 719369 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6129. Min Act: -0.1700
Data Index: 809212 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6289. Min Act: -0.1700
Data Index: 857119 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6450. Min Act: -0.1700
Data Index: 393215 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6129. Min Act: -0.1700
Data Index: 928423 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6129. Min Act: -0.1700
Data Index: 50455 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6129. Min Act: -0.1700
Data Index: 651809 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8048. Min Range: -2.8048
Max Act: 2.6450. Min Act: -0.1700
Data Index: 428180 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19