Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1988 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2302. Min Range: -4.2302
Max Act: 4.1677. Min Act: -0.1700
Data Index: 285491 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2302. Min Range: -4.2302
Max Act: 4.2302. Min Act: -0.1700
Data Index: 1156029 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2302. Min Range: -4.2302
Max Act: 4.1052. Min Act: -0.1700
Data Index: 82958 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.9802. Min Act: -0.1700
Data Index: 991967 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.9802. Min Act: -0.1700
Data Index: 486284 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.9802. Min Act: -0.1700
Data Index: 173629 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2302. Min Range: -4.2302
Max Act: 4.0114. Min Act: -0.1700
Data Index: 280925 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.9489. Min Act: -0.1700
Data Index: 364795 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.8864. Min Act: -0.1700
Data Index: 213235 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.9176. Min Act: -0.1700
Data Index: 605677 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.9176. Min Act: -0.1700
Data Index: 67541 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.9489. Min Act: -0.1700
Data Index: 387032 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.8551. Min Act: -0.1700
Data Index: 1253377 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.9176. Min Act: -0.1700
Data Index: 435308 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.8864. Min Act: -0.1700
Data Index: 1325197 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.9176. Min Act: -0.1700
Data Index: 1047030 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.8864. Min Act: -0.1700
Data Index: 464462 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.8551. Min Act: -0.1700
Data Index: 937414 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.8551. Min Act: -0.1700
Data Index: 1073674 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2302. Min Range: -4.2302
Max Act: 3.8238. Min Act: -0.1700
Data Index: 1039259 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19