Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 897 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.9611. Min Act: -0.1700
Data Index: 80727 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.9453. Min Act: -0.1700
Data Index: 846226 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.9453. Min Act: -0.1700
Data Index: 46673 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.9136. Min Act: -0.1700
Data Index: 437359 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8977. Min Act: -0.1700
Data Index: 531560 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8977. Min Act: -0.1700
Data Index: 1124762 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8660. Min Act: -0.1700
Data Index: 457580 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8342. Min Act: -0.1700
Data Index: 702724 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8183. Min Act: -0.1700
Data Index: 1260736 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8501. Min Act: -0.1700
Data Index: 924974 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8342. Min Act: -0.1700
Data Index: 248389 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.7865. Min Act: -0.1700
Data Index: 531614 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8183. Min Act: -0.1700
Data Index: 495930 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8183. Min Act: -0.1700
Data Index: 1136922 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8342. Min Act: -0.1700
Data Index: 1161014 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.7865. Min Act: -0.1700
Data Index: 570286 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8024. Min Act: -0.1700
Data Index: 606916 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8024. Min Act: -0.1700
Data Index: 401419 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.8024. Min Act: -0.1700
Data Index: 12151 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9611. Min Range: -2.9611
Max Act: 2.7865. Min Act: -0.1700
Data Index: 615445 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19