Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2028 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8843. Min Act: -0.1700
Data Index: 324210 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8843. Min Act: -0.1700
Data Index: 1083924 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8685. Min Act: -0.1700
Data Index: 1207334 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8526. Min Act: -0.1700
Data Index: 20939 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8685. Min Act: -0.1700
Data Index: 201509 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8208. Min Act: -0.1700
Data Index: 1103726 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8208. Min Act: -0.1700
Data Index: 1151990 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8049. Min Act: -0.1700
Data Index: 448887 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8049. Min Act: -0.1700
Data Index: 435643 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8049. Min Act: -0.1699
Data Index: 897776 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8049. Min Act: -0.1700
Data Index: 546073 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.7889. Min Act: -0.1700
Data Index: 80823 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8049. Min Act: -0.1700
Data Index: 1304834 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.7730. Min Act: -0.1700
Data Index: 939512 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.7889. Min Act: -0.1700
Data Index: 1239622 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.8049. Min Act: -0.1699
Data Index: 670472 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.7730. Min Act: -0.1700
Data Index: 712956 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.7730. Min Act: -0.1700
Data Index: 554514 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.7570. Min Act: -0.1700
Data Index: 935634 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8843. Min Range: -2.8843
Max Act: 2.7730. Min Act: -0.1700
Data Index: 1443612 (Python Code)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19