Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1911 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0890. Min Range: -3.0890
Max Act: 3.0890. Min Act: -0.1700
Data Index: 764704 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0890. Min Range: -3.0890
Max Act: 3.0258. Min Act: -0.1700
Data Index: 804471 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0890. Min Range: -3.0890
Max Act: 3.0258. Min Act: -0.1700
Data Index: 755621 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0890. Min Range: -3.0890
Max Act: 3.0100. Min Act: -0.1700
Data Index: 200794 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0890. Min Range: -3.0890
Max Act: 3.0100. Min Act: -0.1700
Data Index: 266989 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9942. Min Act: -0.1700
Data Index: 566370 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9942. Min Act: -0.1700
Data Index: 1159631 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9942. Min Act: -0.1700
Data Index: 383485 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9626. Min Act: -0.1700
Data Index: 93553 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9942. Min Act: -0.1700
Data Index: 83349 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9626. Min Act: -0.1700
Data Index: 211149 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9626. Min Act: -0.1700
Data Index: 405578 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9626. Min Act: -0.1700
Data Index: 1089319 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9626. Min Act: -0.1700
Data Index: 128382 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9626. Min Act: -0.1700
Data Index: 923532 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9468. Min Act: -0.1700
Data Index: 252574 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9309. Min Act: -0.1700
Data Index: 66384 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9468. Min Act: -0.1700
Data Index: 278892 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9468. Min Act: -0.1700
Data Index: 731983 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0890. Min Range: -3.0890
Max Act: 2.9151. Min Act: -0.1700
Data Index: 709241 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19