Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2002 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.9801. Min Act: -0.1700
Data Index: 999378 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.9176. Min Act: -0.1700
Data Index: 209918 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.9488. Min Act: -0.1700
Data Index: 347947 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8863. Min Act: -0.1700
Data Index: 1345157 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8238. Min Act: -0.1700
Data Index: 267085 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8863. Min Act: -0.1700
Data Index: 388483 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8551. Min Act: -0.1700
Data Index: 890009 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8551. Min Act: -0.1700
Data Index: 1312514 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8551. Min Act: -0.1700
Data Index: 850690 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8551. Min Act: -0.1700
Data Index: 351657 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8551. Min Act: -0.1700
Data Index: 377058 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8551. Min Act: -0.1700
Data Index: 1153400 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8238. Min Act: -0.1700
Data Index: 851236 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8238. Min Act: -0.1700
Data Index: 518948 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8238. Min Act: -0.1700
Data Index: 242345 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8551. Min Act: -0.1700
Data Index: 898151 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8551. Min Act: -0.1700
Data Index: 1358654 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.8238. Min Act: -0.1700
Data Index: 711627 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.7613. Min Act: -0.1700
Data Index: 1276229 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9801. Min Range: -4.9801
Max Act: 4.7926. Min Act: -0.1700
Data Index: 143233 (C4 (Web Text))
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19