Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 169 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.1645. Min Act: -0.1700
Data Index: 829761 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.1645. Min Act: -0.1700
Data Index: 2948 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.1228. Min Act: -0.1700
Data Index: 845558 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0810. Min Act: -0.1700
Data Index: 1152606 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0726. Min Act: -0.1700
Data Index: 501157 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0559. Min Act: -0.1700
Data Index: 1617442 (Python Code)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0642. Min Act: -0.1700
Data Index: 1207420 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0559. Min Act: -0.1700
Data Index: 728077 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0559. Min Act: -0.1700
Data Index: 914521 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0474. Min Act: -0.1700
Data Index: 879987 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0390. Min Act: -0.1700
Data Index: 868209 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0306. Min Act: -0.1700
Data Index: 952768 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1645. Min Range: -2.1645
Max Act: 2.0222. Min Act: -0.1700
Data Index: 397211 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1645. Min Range: -2.1645
Max Act: 1.9969. Min Act: -0.1700
Data Index: 658713 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1645. Min Range: -2.1645
Max Act: 1.9884. Min Act: -0.1700
Data Index: 108488 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1645. Min Range: -2.1645
Max Act: 1.9800. Min Act: -0.1700
Data Index: 1287616 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1645. Min Range: -2.1645
Max Act: 1.9800. Min Act: -0.1700
Data Index: 1046207 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1645. Min Range: -2.1645
Max Act: 1.9800. Min Act: -0.1700
Data Index: 191813 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1645. Min Range: -2.1645
Max Act: 1.9800. Min Act: -0.1700
Data Index: 1212231 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1645. Min Range: -2.1645
Max Act: 1.9715. Min Act: -0.1700
Data Index: 1016850 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19