Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1864 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.3098. Min Act: -0.1700
Data Index: 850316 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.2785. Min Act: -0.1700
Data Index: 311629 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.2473. Min Act: -0.1700
Data Index: 957964 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.2160. Min Act: -0.1700
Data Index: 501519 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.1223. Min Act: -0.1700
Data Index: 729315 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.1848. Min Act: -0.1700
Data Index: 119928 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.0910. Min Act: -0.1700
Data Index: 1167686 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.0910. Min Act: -0.1700
Data Index: 1062096 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.0910. Min Act: -0.1699
Data Index: 1296554 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.0597. Min Act: -0.1700
Data Index: 634689 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.0597. Min Act: -0.1700
Data Index: 1307192 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.0285. Min Act: -0.1700
Data Index: 896848 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.0285. Min Act: -0.1700
Data Index: 545971 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3098. Min Range: -4.3098
Max Act: 4.0597. Min Act: -0.1700
Data Index: 1236635 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3098. Min Range: -4.3098
Max Act: 3.9972. Min Act: -0.1700
Data Index: 523305 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3098. Min Range: -4.3098
Max Act: 3.9659. Min Act: -0.1700
Data Index: 387207 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3098. Min Range: -4.3098
Max Act: 3.9972. Min Act: -0.1700
Data Index: 655235 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3098. Min Range: -4.3098
Max Act: 3.9659. Min Act: -0.1700
Data Index: 1224944 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3098. Min Range: -4.3098
Max Act: 3.9972. Min Act: -0.1700
Data Index: 1317505 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3098. Min Range: -4.3098
Max Act: 3.9659. Min Act: -0.1700
Data Index: 132380 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19