Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 32 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.6307. Min Act: -0.1700
Data Index: 1345103 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.6307. Min Act: -0.1700
Data Index: 1006244 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.6307. Min Act: -0.1700
Data Index: 1301537 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.6307. Min Act: -0.1700
Data Index: 423397 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.6146. Min Act: -0.1700
Data Index: 779090 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 324397 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 168514 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5985. Min Act: -0.1700
Data Index: 967329 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 728280 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5985. Min Act: -0.1700
Data Index: 677659 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 740566 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5663. Min Act: -0.1700
Data Index: 528869 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5663. Min Act: -0.1700
Data Index: 776564 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 792514 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5663. Min Act: -0.1700
Data Index: 1145899 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 762836 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 65953 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 737352 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 74524 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6307. Min Range: -2.6307
Max Act: 2.5824. Min Act: -0.1700
Data Index: 155391 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19