Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 276 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.5217. Min Act: -0.1700
Data Index: 1499613 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.5055. Min Act: -0.1700
Data Index: 268180 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.5055. Min Act: -0.1700
Data Index: 852963 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4893. Min Act: -0.1700
Data Index: 432506 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4568. Min Act: -0.1700
Data Index: 570527 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4568. Min Act: -0.1700
Data Index: 1527287 (Python Code)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4243. Min Act: -0.1700
Data Index: 1637329 (Python Code)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4406. Min Act: -0.1700
Data Index: 908704 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4243. Min Act: -0.1700
Data Index: 125993 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4243. Min Act: -0.1700
Data Index: 141585 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4243. Min Act: -0.1700
Data Index: 29542 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4243. Min Act: -0.1700
Data Index: 423819 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4080. Min Act: -0.1700
Data Index: 559900 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4080. Min Act: -0.1700
Data Index: 1607902 (Python Code)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.3917. Min Act: -0.1700
Data Index: 1386331 (Python Code)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.3917. Min Act: -0.1700
Data Index: 709420 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.4080. Min Act: -0.1700
Data Index: 715894 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.3917. Min Act: -0.1700
Data Index: 967995 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.3917. Min Act: -0.1700
Data Index: 967321 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5217. Min Range: -2.5217
Max Act: 2.3917. Min Act: -0.1700
Data Index: 1513202 (Python Code)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19