Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 282 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.2785. Min Act: -0.1700
Data Index: 569867 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.2472. Min Act: -0.1700
Data Index: 907021 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.2316. Min Act: -0.1700
Data Index: 178719 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.2316. Min Act: -0.1700
Data Index: 956797 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.2160. Min Act: -0.1700
Data Index: 796640 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.2003. Min Act: -0.1700
Data Index: 54474 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.1535. Min Act: -0.1700
Data Index: 1314782 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.1222. Min Act: -0.1700
Data Index: 520638 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.1535. Min Act: -0.1700
Data Index: 207110 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.1378. Min Act: -0.1700
Data Index: 431146 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.1378. Min Act: -0.1700
Data Index: 1270777 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.1378. Min Act: -0.1700
Data Index: 106594 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.1222. Min Act: -0.1700
Data Index: 1283014 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.0753. Min Act: -0.1700
Data Index: 608953 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.0909. Min Act: -0.1700
Data Index: 308236 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.0909. Min Act: -0.1700
Data Index: 311050 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.0909. Min Act: -0.1700
Data Index: 465015 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.0909. Min Act: -0.1700
Data Index: 60924 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.0909. Min Act: -0.1700
Data Index: 1210903 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2785. Min Range: -4.2785
Max Act: 4.0909. Min Act: -0.1700
Data Index: 1180541 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19