Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1877 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.1860. Min Act: -0.1700
Data Index: 958481 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.1235. Min Act: -0.1700
Data Index: 174255 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.0610. Min Act: -0.1700
Data Index: 1345569 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.0610. Min Act: -0.1700
Data Index: 1355572 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.0610. Min Act: -0.1700
Data Index: 791543 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.0610. Min Act: -0.1700
Data Index: 581548 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.0297. Min Act: -0.1700
Data Index: 327687 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.0610. Min Act: -0.1700
Data Index: 46453 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.0297. Min Act: -0.1700
Data Index: 1315325 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9985. Min Act: -0.1700
Data Index: 175509 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9985. Min Act: -0.1700
Data Index: 1029691 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9985. Min Act: -0.1700
Data Index: 1286178 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9985. Min Act: -0.1700
Data Index: 1243744 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9672. Min Act: -0.1700
Data Index: 803200 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9985. Min Act: -0.1700
Data Index: 1084231 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9672. Min Act: -0.1700
Data Index: 740380 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9985. Min Act: -0.1700
Data Index: 1066332 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9985. Min Act: -0.1700
Data Index: 684766 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1860. Min Range: -4.1860
Max Act: 3.9985. Min Act: -0.1700
Data Index: 327125 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1860. Min Range: -4.1860
Max Act: 4.0297. Min Act: -0.1700
Data Index: 529550 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19