Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 149 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.3178. Min Act: -0.1700
Data Index: 1091178 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.3490. Min Act: -0.1700
Data Index: 930758 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.3178. Min Act: -0.1700
Data Index: 1347361 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.2865. Min Act: -0.1700
Data Index: 731926 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.2553. Min Act: -0.1700
Data Index: 1250852 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.2553. Min Act: -0.1700
Data Index: 665019 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.2553. Min Act: -0.1700
Data Index: 1308782 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.2240. Min Act: -0.1700
Data Index: 651438 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.2240. Min Act: -0.1700
Data Index: 556678 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.1928. Min Act: -0.1700
Data Index: 1198077 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.1928. Min Act: -0.1700
Data Index: 770959 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.1928. Min Act: -0.1700
Data Index: 396629 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.1928. Min Act: -0.1700
Data Index: 727359 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.0990. Min Act: -0.1700
Data Index: 1093069 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.0990. Min Act: -0.1700
Data Index: 1155594 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3490. Min Range: -4.3490
Max Act: 4.0677. Min Act: -0.1700
Data Index: 1147062 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3490. Min Range: -4.3490
Max Act: 3.5828. Min Act: -0.1700
Data Index: 1309261 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3490. Min Range: -4.3490
Max Act: 3.5515. Min Act: -0.1700
Data Index: 1023479 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3490. Min Range: -4.3490
Max Act: 3.5515. Min Act: -0.1700
Data Index: 1245919 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3490. Min Range: -4.3490
Max Act: 3.5202. Min Act: -0.1700
Data Index: 909565 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19