Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 278 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.4826. Min Act: -0.1700
Data Index: 80602 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.4201. Min Act: -0.1700
Data Index: 1166404 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.4201. Min Act: -0.1700
Data Index: 400061 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.4201. Min Act: -0.1700
Data Index: 859909 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.4826. Min Act: -0.1700
Data Index: 423543 (C4 (Web Text))
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.4826. Min Act: -0.1700
Data Index: 618621 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.3576. Min Act: -0.1700
Data Index: 619468 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.3576. Min Act: -0.1700
Data Index: 1473591 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.3263. Min Act: -0.1700
Data Index: 529733 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.3888. Min Act: -0.1700
Data Index: 1192745 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.3263. Min Act: -0.1700
Data Index: 1265542 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.3576. Min Act: -0.1700
Data Index: 266363 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.2951. Min Act: -0.1700
Data Index: 968480 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.3263. Min Act: -0.1700
Data Index: 214541 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.2638. Min Act: -0.1700
Data Index: 782309 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.3576. Min Act: -0.1700
Data Index: 1395833 (Python Code)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.2951. Min Act: -0.1700
Data Index: 1373592 (Python Code)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.2951. Min Act: -0.1700
Data Index: 1646832 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.2951. Min Act: -0.1700
Data Index: 1571489 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4826. Min Range: -4.4826
Max Act: 4.2638. Min Act: -0.1700
Data Index: 1633572 (Python Code)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19