Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 783 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.4059. Min Act: -0.1700
Data Index: 756672 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.4059. Min Act: -0.1700
Data Index: 1258239 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.3732. Min Act: -0.1700
Data Index: 1295612 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.3569. Min Act: -0.1700
Data Index: 506533 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.3569. Min Act: -0.1700
Data Index: 687265 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.3241. Min Act: -0.1700
Data Index: 868831 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.3405. Min Act: -0.1700
Data Index: 338125 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.3241. Min Act: -0.1700
Data Index: 359378 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.3077. Min Act: -0.1700
Data Index: 253104 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2913. Min Act: -0.1700
Data Index: 791293 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2913. Min Act: -0.1700
Data Index: 802526 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2913. Min Act: -0.1700
Data Index: 367714 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.3077. Min Act: -0.1700
Data Index: 632390 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2583. Min Act: -0.1700
Data Index: 628762 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2748. Min Act: -0.1700
Data Index: 53317 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2583. Min Act: -0.1700
Data Index: 561006 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2748. Min Act: -0.1700
Data Index: 425790 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2748. Min Act: -0.1700
Data Index: 569521 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2748. Min Act: -0.1700
Data Index: 500698 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4059. Min Range: -2.4059
Max Act: 2.2748. Min Act: -0.1700
Data Index: 115348 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19