Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1405 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.0819. Min Range: -5.0819
Max Act: 5.0194. Min Act: -0.1700
Data Index: 191470 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0819. Min Range: -5.0819
Max Act: 5.0819. Min Act: -0.1700
Data Index: 675104 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8944. Min Act: -0.1700
Data Index: 367394 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.9569. Min Act: -0.1700
Data Index: 385835 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8631. Min Act: -0.1700
Data Index: 339692 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8319. Min Act: -0.1700
Data Index: 260539 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8319. Min Act: -0.1700
Data Index: 635808 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8631. Min Act: -0.1700
Data Index: 1009188 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8631. Min Act: -0.1700
Data Index: 872445 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8006. Min Act: -0.1700
Data Index: 1101854 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8631. Min Act: -0.1700
Data Index: 598176 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8631. Min Act: -0.1700
Data Index: 984306 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8006. Min Act: -0.1700
Data Index: 895407 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.7694. Min Act: -0.1700
Data Index: 833083 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.7694. Min Act: -0.1700
Data Index: 1356333 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.8006. Min Act: -0.1700
Data Index: 406702 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.7069. Min Act: -0.1700
Data Index: 179703 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.6756. Min Act: -0.1700
Data Index: 61860 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.7694. Min Act: -0.1700
Data Index: 657341 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0819. Min Range: -5.0819
Max Act: 4.7381. Min Act: -0.1700
Data Index: 41944 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19