Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 752 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.6559. Min Act: -0.1700
Data Index: 858080 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.6715. Min Act: -0.1700
Data Index: 433056 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.6402. Min Act: -0.1700
Data Index: 130354 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.5932. Min Act: -0.1700
Data Index: 1120438 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.5463. Min Act: -0.1700
Data Index: 901285 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.5619. Min Act: -0.1700
Data Index: 831818 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.5463. Min Act: -0.1700
Data Index: 149394 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.5463. Min Act: -0.1700
Data Index: 303510 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.5306. Min Act: -0.1700
Data Index: 464932 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4993. Min Act: -0.1700
Data Index: 1010461 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.5306. Min Act: -0.1700
Data Index: 541902 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4993. Min Act: -0.1700
Data Index: 220672 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4679. Min Act: -0.1700
Data Index: 124440 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4366. Min Act: -0.1700
Data Index: 841445 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4522. Min Act: -0.1700
Data Index: 722655 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4209. Min Act: -0.1700
Data Index: 1052737 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4052. Min Act: -0.1700
Data Index: 264724 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4209. Min Act: -0.1700
Data Index: 1068744 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4209. Min Act: -0.1700
Data Index: 1191867 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6715. Min Range: -3.6715
Max Act: 3.4052. Min Act: -0.1700
Data Index: 255666 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19