Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1786 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0891. Min Range: -3.0891
Max Act: 3.0891. Min Act: -0.1700
Data Index: 338202 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0891. Min Range: -3.0891
Max Act: 3.0576. Min Act: -0.1700
Data Index: 156627 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0891. Min Range: -3.0891
Max Act: 3.0418. Min Act: -0.1700
Data Index: 302429 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0891. Min Range: -3.0891
Max Act: 3.0260. Min Act: -0.1700
Data Index: 1355123 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0891. Min Range: -3.0891
Max Act: 3.0418. Min Act: -0.1700
Data Index: 769129 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0891. Min Range: -3.0891
Max Act: 3.0102. Min Act: -0.1700
Data Index: 620576 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9469. Min Act: -0.1700
Data Index: 123026 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9944. Min Act: -0.1700
Data Index: 246402 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9944. Min Act: -0.1700
Data Index: 1256276 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9944. Min Act: -0.1700
Data Index: 1356784 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9786. Min Act: -0.1700
Data Index: 1483378 (Python Code)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9786. Min Act: -0.1700
Data Index: 168589 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9786. Min Act: -0.1700
Data Index: 592764 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9786. Min Act: -0.1700
Data Index: 31515 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9944. Min Act: -0.1700
Data Index: 329398 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9311. Min Act: -0.1700
Data Index: 1308190 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9786. Min Act: -0.1700
Data Index: 1289233 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9786. Min Act: -0.1700
Data Index: 640431 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9628. Min Act: -0.1700
Data Index: 1186117 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0891. Min Range: -3.0891
Max Act: 2.9628. Min Act: -0.1700
Data Index: 1135593 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19