Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 10 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.2097. Min Range: -6.2097
Max Act: 6.2097. Min Act: -0.1700
Data Index: 139659 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2097. Min Range: -6.2097
Max Act: 6.2097. Min Act: -0.1700
Data Index: 173706 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2097. Min Range: -6.2097
Max Act: 6.1784. Min Act: -0.1700
Data Index: 165686 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2097. Min Range: -6.2097
Max Act: 6.0847. Min Act: -0.1700
Data Index: 943888 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2097. Min Range: -6.2097
Max Act: 6.0534. Min Act: -0.1700
Data Index: 1042043 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2097. Min Range: -6.2097
Max Act: 6.1159. Min Act: -0.1700
Data Index: 985906 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.9909. Min Act: -0.1700
Data Index: 631220 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.9597. Min Act: -0.1700
Data Index: 256491 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2097. Min Range: -6.2097
Max Act: 6.0534. Min Act: -0.1700
Data Index: 1167315 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.9597. Min Act: -0.1700
Data Index: 912134 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.9284. Min Act: -0.1700
Data Index: 694896 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.8972. Min Act: -0.1700
Data Index: 1246714 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.6784. Min Act: -0.1700
Data Index: 927066 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.5847. Min Act: -0.1700
Data Index: 571225 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.5534. Min Act: -0.1700
Data Index: 428313 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.5534. Min Act: -0.1700
Data Index: 390730 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.4909. Min Act: -0.1700
Data Index: 713383 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.5847. Min Act: -0.1700
Data Index: 192979 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.5534. Min Act: -0.1700
Data Index: 441157 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2097. Min Range: -6.2097
Max Act: 5.5534. Min Act: -0.1700
Data Index: 284674 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19