Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 838 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.2780. Min Act: -0.1700
Data Index: 70614 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.2450. Min Act: -0.1700
Data Index: 255751 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.2450. Min Act: -0.1700
Data Index: 119404 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.2119. Min Act: -0.1700
Data Index: 865267 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1953. Min Act: -0.1700
Data Index: 482873 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1953. Min Act: -0.1700
Data Index: 618078 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1953. Min Act: -0.1700
Data Index: 526385 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1953. Min Act: -0.1700
Data Index: 416792 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1621. Min Act: -0.1700
Data Index: 1150801 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1953. Min Act: -0.1700
Data Index: 1022121 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1787. Min Act: -0.1700
Data Index: 238407 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1787. Min Act: -0.1700
Data Index: 664458 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1787. Min Act: -0.1700
Data Index: 1163072 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1621. Min Act: -0.1700
Data Index: 523918 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1454. Min Act: -0.1700
Data Index: 642635 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1621. Min Act: -0.1700
Data Index: 1215734 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1621. Min Act: -0.1700
Data Index: 1071644 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1454. Min Act: -0.1700
Data Index: 1157280 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1454. Min Act: -0.1700
Data Index: 685157 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2780. Min Range: -2.2780
Max Act: 2.1288. Min Act: -0.1700
Data Index: 636720 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19