Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 35 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.9950. Min Act: -0.1700
Data Index: 612279 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0575. Min Range: -5.0575
Max Act: 5.0575. Min Act: -0.1700
Data Index: 1014918 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.8388. Min Act: -0.1700
Data Index: 886796 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.9638. Min Act: -0.1700
Data Index: 134514 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.9013. Min Act: -0.1700
Data Index: 375205 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.8700. Min Act: -0.1700
Data Index: 1172118 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.8075. Min Act: -0.1700
Data Index: 45688 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.8075. Min Act: -0.1700
Data Index: 478619 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.9013. Min Act: -0.1700
Data Index: 335854 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.8388. Min Act: -0.1700
Data Index: 517062 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.7763. Min Act: -0.1700
Data Index: 482206 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.7450. Min Act: -0.1700
Data Index: 857579 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.7763. Min Act: -0.1700
Data Index: 786735 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.8388. Min Act: -0.1700
Data Index: 1231363 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.8388. Min Act: -0.1700
Data Index: 258249 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.6981. Min Act: -0.1700
Data Index: 256568 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.8075. Min Act: -0.1700
Data Index: 699198 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.7138. Min Act: -0.1700
Data Index: 446167 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.8388. Min Act: -0.1700
Data Index: 333138 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0575. Min Range: -5.0575
Max Act: 4.7294. Min Act: -0.1700
Data Index: 576211 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19