Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1781 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.8088. Min Act: -0.1700
Data Index: 84691 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7770. Min Act: -0.1700
Data Index: 701031 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7929. Min Act: -0.1700
Data Index: 101252 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7770. Min Act: -0.1700
Data Index: 1197002 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7610. Min Act: -0.1700
Data Index: 1138807 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7610. Min Act: -0.1700
Data Index: 226267 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7610. Min Act: -0.1700
Data Index: 176710 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7610. Min Act: -0.1700
Data Index: 880399 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7451. Min Act: -0.1700
Data Index: 130503 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7451. Min Act: -0.1700
Data Index: 908998 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7451. Min Act: -0.1700
Data Index: 1357717 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7451. Min Act: -0.1700
Data Index: 947743 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7451. Min Act: -0.1700
Data Index: 532227 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7291. Min Act: -0.1700
Data Index: 95577 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7291. Min Act: -0.1700
Data Index: 1211555 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7291. Min Act: -0.1700
Data Index: 126459 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7131. Min Act: -0.1700
Data Index: 1275762 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7291. Min Act: -0.1700
Data Index: 51100 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7291. Min Act: -0.1700
Data Index: 1311797 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8088. Min Range: -2.8088
Max Act: 2.7291. Min Act: -0.1700
Data Index: 631318 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19