Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1965 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0628. Min Range: -3.0628
Max Act: 3.0628. Min Act: -0.1700
Data Index: 961169 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.8729. Min Act: -0.1700
Data Index: 1152177 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.8570. Min Act: -0.1700
Data Index: 72240 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.8252. Min Act: -0.1700
Data Index: 303731 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7933. Min Act: -0.1700
Data Index: 1174800 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.8093. Min Act: -0.1700
Data Index: 831908 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.8093. Min Act: -0.1700
Data Index: 147981 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7774. Min Act: -0.1700
Data Index: 869105 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7774. Min Act: -0.1700
Data Index: 905155 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7455. Min Act: -0.1700
Data Index: 15085 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7774. Min Act: -0.1700
Data Index: 149474 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7295. Min Act: -0.1700
Data Index: 1087468 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7455. Min Act: -0.1700
Data Index: 66362 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7295. Min Act: -0.1700
Data Index: 996624 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7455. Min Act: -0.1700
Data Index: 668413 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7295. Min Act: -0.1700
Data Index: 789621 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7135. Min Act: -0.1700
Data Index: 499391 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7135. Min Act: -0.1700
Data Index: 210542 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.7295. Min Act: -0.1700
Data Index: 53178 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0628. Min Range: -3.0628
Max Act: 2.6975. Min Act: -0.1700
Data Index: 927865 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19