Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 87 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1151. Min Range: -4.1151
Max Act: 4.1151. Min Act: -0.1700
Data Index: 460617 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.9900. Min Act: -0.1700
Data Index: 826546 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.9275. Min Act: -0.1700
Data Index: 570362 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.8962. Min Act: -0.1700
Data Index: 519357 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.8649. Min Act: -0.1700
Data Index: 583740 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.8336. Min Act: -0.1700
Data Index: 685777 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.8649. Min Act: -0.1700
Data Index: 1015884 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.8336. Min Act: -0.1700
Data Index: 390787 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.7711. Min Act: -0.1700
Data Index: 628938 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.8024. Min Act: -0.1700
Data Index: 1144790 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.8336. Min Act: -0.1700
Data Index: 1033291 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.7398. Min Act: -0.1700
Data Index: 1015966 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.7711. Min Act: -0.1700
Data Index: 567769 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.7711. Min Act: -0.1700
Data Index: 645828 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.8024. Min Act: -0.1700
Data Index: 305464 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.7398. Min Act: -0.1700
Data Index: 1354593 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.8024. Min Act: -0.1700
Data Index: 1031216 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.7241. Min Act: -0.1700
Data Index: 308455 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.7398. Min Act: -0.1700
Data Index: 523340 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1151. Min Range: -4.1151
Max Act: 3.7711. Min Act: -0.1700
Data Index: 818275 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19