Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 170 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.2920. Min Act: -0.1700
Data Index: 941303 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.3233. Min Act: -0.1700
Data Index: 131306 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.2607. Min Act: -0.1700
Data Index: 1347386 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.2607. Min Act: -0.1700
Data Index: 155736 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.1982. Min Act: -0.1700
Data Index: 383721 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.1670. Min Act: -0.1700
Data Index: 891685 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.1357. Min Act: -0.1700
Data Index: 866246 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0419. Min Act: -0.1700
Data Index: 1203944 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0732. Min Act: -0.1700
Data Index: 284366 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0419. Min Act: -0.1700
Data Index: 1166220 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0732. Min Act: -0.1700
Data Index: 251808 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0419. Min Act: -0.1700
Data Index: 246954 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0107. Min Act: -0.1700
Data Index: 159459 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0419. Min Act: -0.1700
Data Index: 320096 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0419. Min Act: -0.1700
Data Index: 740677 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0107. Min Act: -0.1700
Data Index: 130143 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3233. Min Range: -4.3233
Max Act: 3.9481. Min Act: -0.1700
Data Index: 1189386 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0107. Min Act: -0.1700
Data Index: 128575 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0419. Min Act: -0.1700
Data Index: 440158 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3233. Min Range: -4.3233
Max Act: 4.0419. Min Act: -0.1700
Data Index: 777270 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19