Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2013 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.5815. Min Act: -0.1700
Data Index: 480558 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.5503. Min Act: -0.1700
Data Index: 176861 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4878. Min Act: -0.1700
Data Index: 935058 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4878. Min Act: -0.1700
Data Index: 544606 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.5503. Min Act: -0.1700
Data Index: 18762 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.5190. Min Act: -0.1700
Data Index: 58934 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.5190. Min Act: -0.1700
Data Index: 1149723 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.5503. Min Act: -0.1700
Data Index: 860714 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4878. Min Act: -0.1700
Data Index: 638768 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4878. Min Act: -0.1700
Data Index: 1279107 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4878. Min Act: -0.1700
Data Index: 1015480 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4878. Min Act: -0.1700
Data Index: 974299 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4878. Min Act: -0.1700
Data Index: 722397 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4253. Min Act: -0.1700
Data Index: 854476 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4565. Min Act: -0.1700
Data Index: 301659 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4253. Min Act: -0.1700
Data Index: 687233 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4253. Min Act: -0.1700
Data Index: 211273 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4253. Min Act: -0.1700
Data Index: 1135494 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.3940. Min Act: -0.1700
Data Index: 889555 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5815. Min Range: -4.5815
Max Act: 4.4565. Min Act: -0.1700
Data Index: 543371 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19