Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 33 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.3243. Min Act: -0.1700
Data Index: 52931 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.3079. Min Act: -0.1700
Data Index: 216674 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.3079. Min Act: -0.1700
Data Index: 594514 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2915. Min Act: -0.1700
Data Index: 1041974 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.3079. Min Act: -0.1700
Data Index: 1308656 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2585. Min Act: -0.1700
Data Index: 986039 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2750. Min Act: -0.1700
Data Index: 626559 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2585. Min Act: -0.1700
Data Index: 557704 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2585. Min Act: -0.1700
Data Index: 24869 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2585. Min Act: -0.1700
Data Index: 284997 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2585. Min Act: -0.1700
Data Index: 273725 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2585. Min Act: -0.1700
Data Index: 39432 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2420. Min Act: -0.1700
Data Index: 759599 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2420. Min Act: -0.1700
Data Index: 70122 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2420. Min Act: -0.1700
Data Index: 466930 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2420. Min Act: -0.1700
Data Index: 98458 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2420. Min Act: -0.1700
Data Index: 836689 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2420. Min Act: -0.1700
Data Index: 495216 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2420. Min Act: -0.1700
Data Index: 87335 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3243. Min Range: -2.3243
Max Act: 2.2255. Min Act: -0.1700
Data Index: 483189 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19