Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 11 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3294. Min Range: -4.3294
Max Act: 4.3294. Min Act: -0.1700
Data Index: 1206269 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3294. Min Range: -4.3294
Max Act: 4.2200. Min Act: -0.1700
Data Index: 53435 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3294. Min Range: -4.3294
Max Act: 4.1263. Min Act: -0.1700
Data Index: 570689 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3294. Min Range: -4.3294
Max Act: 4.0168. Min Act: -0.1700
Data Index: 887690 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9543. Min Act: -0.1700
Data Index: 1198951 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.8918. Min Act: -0.1700
Data Index: 863222 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9699. Min Act: -0.1700
Data Index: 212768 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9699. Min Act: -0.1700
Data Index: 596334 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9699. Min Act: -0.1700
Data Index: 1069956 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9699. Min Act: -0.1700
Data Index: 1086079 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9230. Min Act: -0.1700
Data Index: 515770 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9230. Min Act: -0.1700
Data Index: 539431 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9387. Min Act: -0.1700
Data Index: 595963 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9387. Min Act: -0.1700
Data Index: 420666 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.8918. Min Act: -0.1700
Data Index: 741367 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.8761. Min Act: -0.1700
Data Index: 961522 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.8605. Min Act: -0.1700
Data Index: 933395 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.9074. Min Act: -0.1700
Data Index: 1113779 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.8761. Min Act: -0.1700
Data Index: 277051 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3294. Min Range: -4.3294
Max Act: 3.8605. Min Act: -0.1700
Data Index: 19748 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19