Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 163 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.5401. Min Act: -0.1700
Data Index: 133681 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.4464. Min Act: -0.1700
Data Index: 1059000 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.4776. Min Act: -0.1700
Data Index: 1048673 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3526. Min Act: -0.1700
Data Index: 574302 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.4151. Min Act: -0.1700
Data Index: 527708 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.2901. Min Act: -0.1700
Data Index: 72417 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3839. Min Act: -0.1700
Data Index: 336478 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3839. Min Act: -0.1700
Data Index: 127230 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3526. Min Act: -0.1700
Data Index: 767829 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3839. Min Act: -0.1700
Data Index: 566475 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3526. Min Act: -0.1700
Data Index: 77162 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3214. Min Act: -0.1700
Data Index: 361690 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.2901. Min Act: -0.1700
Data Index: 1214785 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3214. Min Act: -0.1700
Data Index: 289896 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3214. Min Act: -0.1700
Data Index: 903841 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.2901. Min Act: -0.1700
Data Index: 761563 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.3839. Min Act: -0.1700
Data Index: 641086 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.2276. Min Act: -0.1700
Data Index: 228607 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.2588. Min Act: -0.1700
Data Index: 46373 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5401. Min Range: -4.5401
Max Act: 4.2901. Min Act: -0.1700
Data Index: 741996 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19