Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 247 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.5365. Min Act: -0.1700
Data Index: 926950 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.4115. Min Act: -0.1700
Data Index: 458070 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.4427. Min Act: -0.1700
Data Index: 543477 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.3490. Min Act: -0.1700
Data Index: 1091592 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.3490. Min Act: -0.1700
Data Index: 1302959 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.3177. Min Act: -0.1700
Data Index: 1025297 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.3177. Min Act: -0.1700
Data Index: 1328354 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.2865. Min Act: -0.1700
Data Index: 596939 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.3177. Min Act: -0.1700
Data Index: 696407 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.2240. Min Act: -0.1700
Data Index: 175671 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.2552. Min Act: -0.1700
Data Index: 349725 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.2240. Min Act: -0.1700
Data Index: 954676 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.2552. Min Act: -0.1700
Data Index: 471525 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.2240. Min Act: -0.1700
Data Index: 819252 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.1614. Min Act: -0.1700
Data Index: 248591 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.2552. Min Act: -0.1700
Data Index: 311857 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.2552. Min Act: -0.1700
Data Index: 677638 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.1927. Min Act: -0.1700
Data Index: 838789 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.1614. Min Act: -0.1700
Data Index: 444558 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5365. Min Range: -4.5365
Max Act: 4.1927. Min Act: -0.1700
Data Index: 318957 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19