Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 206 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.7402. Min Act: -0.1700
Data Index: 579805 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.6441. Min Act: -0.1700
Data Index: 879763 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.5798. Min Act: -0.1700
Data Index: 846167 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.5637. Min Act: -0.1700
Data Index: 153952 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.5637. Min Act: -0.1700
Data Index: 306243 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.5637. Min Act: -0.1700
Data Index: 801895 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.5476. Min Act: -0.1700
Data Index: 108378 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.5314. Min Act: -0.1700
Data Index: 804643 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.4990. Min Act: -0.1700
Data Index: 117048 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.5152. Min Act: -0.1700
Data Index: 883795 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.5152. Min Act: -0.1700
Data Index: 1076267 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.5152. Min Act: -0.1700
Data Index: 435370 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.4828. Min Act: -0.1700
Data Index: 212678 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.4990. Min Act: -0.1700
Data Index: 307337 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.4990. Min Act: -0.1700
Data Index: 554219 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.4990. Min Act: -0.1700
Data Index: 144220 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.4666. Min Act: -0.1700
Data Index: 1307779 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.4990. Min Act: -0.1700
Data Index: 1324661 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.4990. Min Act: -0.1700
Data Index: 480497 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7402. Min Range: -2.7402
Max Act: 2.4828. Min Act: -0.1700
Data Index: 1490191 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19