Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2012 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.6848. Min Act: -0.1700
Data Index: 242313 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.6413. Min Act: -0.1700
Data Index: 1283291 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.6326. Min Act: -0.1698
Data Index: 927604 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.6326. Min Act: -0.1700
Data Index: 570511 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.6239. Min Act: -0.1700
Data Index: 938570 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.6152. Min Act: -0.1700
Data Index: 772872 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5977. Min Act: -0.1700
Data Index: 365633 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5977. Min Act: -0.1700
Data Index: 4055 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5977. Min Act: -0.1700
Data Index: 310125 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5803. Min Act: -0.1700
Data Index: 418179 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5890. Min Act: -0.1700
Data Index: 470854 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5977. Min Act: -0.1700
Data Index: 1022440 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5890. Min Act: -0.1699
Data Index: 421115 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5803. Min Act: -0.1700
Data Index: 1175148 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5803. Min Act: -0.1700
Data Index: 1122699 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5715. Min Act: -0.1700
Data Index: 863747 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5715. Min Act: -0.1700
Data Index: 947887 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5628. Min Act: -0.1692
Data Index: 360862 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5540. Min Act: -0.1699
Data Index: 1389508 (Python Code)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6848. Min Range: -1.6848
Max Act: 1.5628. Min Act: -0.1699
Data Index: 305147 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19