Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 12 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0204. Min Range: -3.0204
Max Act: 3.0204. Min Act: -0.1700
Data Index: 246185 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0204. Min Range: -3.0204
Max Act: 3.0046. Min Act: -0.1700
Data Index: 202120 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9888. Min Act: -0.1700
Data Index: 1291696 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9571. Min Act: -0.1700
Data Index: 1329559 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9413. Min Act: -0.1700
Data Index: 680950 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9255. Min Act: -0.1700
Data Index: 782343 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9413. Min Act: -0.1700
Data Index: 956358 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9255. Min Act: -0.1700
Data Index: 173533 (C4 (Web Text))
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9255. Min Act: -0.1700
Data Index: 233565 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9096. Min Act: -0.1700
Data Index: 1107050 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9096. Min Act: -0.1700
Data Index: 916078 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.8779. Min Act: -0.1700
Data Index: 153218 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.9096. Min Act: -0.1700
Data Index: 640170 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.8779. Min Act: -0.1700
Data Index: 172015 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.8620. Min Act: -0.1700
Data Index: 1112162 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.8779. Min Act: -0.1700
Data Index: 1168337 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.8302. Min Act: -0.1700
Data Index: 592179 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.8461. Min Act: -0.1700
Data Index: 260907 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.8620. Min Act: -0.1700
Data Index: 124814 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0204. Min Range: -3.0204
Max Act: 2.8620. Min Act: -0.1700
Data Index: 785538 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19