Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 777 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.5419. Min Act: -0.1700
Data Index: 1127245 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4772. Min Act: -0.1700
Data Index: 288236 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4772. Min Act: -0.1700
Data Index: 248520 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4609. Min Act: -0.1700
Data Index: 346926 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4447. Min Act: -0.1700
Data Index: 477626 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4447. Min Act: -0.1700
Data Index: 668683 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4284. Min Act: -0.1700
Data Index: 805897 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4447. Min Act: -0.1700
Data Index: 694245 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4447. Min Act: -0.1700
Data Index: 394507 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4284. Min Act: -0.1700
Data Index: 1334935 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4284. Min Act: -0.1700
Data Index: 1315633 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4284. Min Act: -0.1700
Data Index: 824390 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4284. Min Act: -0.1700
Data Index: 512874 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4121. Min Act: -0.1700
Data Index: 885077 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4121. Min Act: -0.1700
Data Index: 880473 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4121. Min Act: -0.1700
Data Index: 673207 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4121. Min Act: -0.1700
Data Index: 1157497 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4121. Min Act: -0.1700
Data Index: 112725 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4121. Min Act: -0.1700
Data Index: 577888 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5419. Min Range: -2.5419
Max Act: 2.4121. Min Act: -0.1700
Data Index: 810329 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19