Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1989 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.8024. Min Act: -0.1700
Data Index: 649936 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7864. Min Act: -0.1700
Data Index: 875372 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7864. Min Act: -0.1700
Data Index: 1248822 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7864. Min Act: -0.1700
Data Index: 966086 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7705. Min Act: -0.1700
Data Index: 324084 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7546. Min Act: -0.1700
Data Index: 1150340 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7386. Min Act: -0.1700
Data Index: 1039639 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7386. Min Act: -0.1700
Data Index: 1283137 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7546. Min Act: -0.1700
Data Index: 325963 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7226. Min Act: -0.1700
Data Index: 1188882 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.7226. Min Act: -0.1700
Data Index: 695587 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.6906. Min Act: -0.1700
Data Index: 930969 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.6906. Min Act: -0.1700
Data Index: 597180 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.6906. Min Act: -0.1700
Data Index: 1136143 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.6906. Min Act: -0.1700
Data Index: 256736 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.6746. Min Act: -0.1700
Data Index: 738253 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.6906. Min Act: -0.1700
Data Index: 291264 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.6906. Min Act: -0.1700
Data Index: 1107330 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.6906. Min Act: -0.1700
Data Index: 580914 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8024. Min Range: -2.8024
Max Act: 2.6906. Min Act: -0.1700
Data Index: 532761 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19