Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 587 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0100. Min Range: -3.0100
Max Act: 3.0100. Min Act: -0.1700
Data Index: 1301213 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.9467. Min Act: -0.1700
Data Index: 310216 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.9308. Min Act: -0.1700
Data Index: 411251 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.9308. Min Act: -0.1700
Data Index: 354622 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.9150. Min Act: -0.1700
Data Index: 1512213 (Python Code)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.9150. Min Act: -0.1700
Data Index: 83756 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8991. Min Act: -0.1700
Data Index: 921163 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8833. Min Act: -0.1700
Data Index: 631770 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8833. Min Act: -0.1700
Data Index: 1357048 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8833. Min Act: -0.1700
Data Index: 577372 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8991. Min Act: -0.1700
Data Index: 1171263 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8674. Min Act: -0.1700
Data Index: 15639 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8515. Min Act: -0.1700
Data Index: 1042421 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8674. Min Act: -0.1700
Data Index: 120453 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8515. Min Act: -0.1700
Data Index: 832994 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8515. Min Act: -0.1700
Data Index: 1296315 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8515. Min Act: -0.1700
Data Index: 814231 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8674. Min Act: -0.1700
Data Index: 262116 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8674. Min Act: -0.1700
Data Index: 1282492 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0100. Min Range: -3.0100
Max Act: 2.8674. Min Act: -0.1700
Data Index: 671494 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19