Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 584 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7682. Min Act: -0.1700
Data Index: 1034760 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7523. Min Act: -0.1700
Data Index: 54791 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7523. Min Act: -0.1700
Data Index: 104457 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7682. Min Act: -0.1699
Data Index: 370878 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7682. Min Act: -0.1700
Data Index: 474507 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7203. Min Act: -0.1700
Data Index: 1048904 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7203. Min Act: -0.1699
Data Index: 1593903 (Python Code)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7043. Min Act: -0.1700
Data Index: 1050843 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7043. Min Act: -0.1700
Data Index: 278186 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.7203. Min Act: -0.1700
Data Index: 403946 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6883. Min Act: -0.1700
Data Index: 120152 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6883. Min Act: -0.1700
Data Index: 552243 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6563. Min Act: -0.1700
Data Index: 682907 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6563. Min Act: -0.1700
Data Index: 1232649 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6402. Min Act: -0.1700
Data Index: 1173532 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6563. Min Act: -0.1700
Data Index: 1272741 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6563. Min Act: -0.1700
Data Index: 642362 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6563. Min Act: -0.1700
Data Index: 1535976 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6402. Min Act: -0.1700
Data Index: 617799 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7682. Min Range: -2.7682
Max Act: 2.6081. Min Act: -0.1700
Data Index: 484237 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19