Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1648 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.0767. Min Range: -2.0767
Max Act: 2.0767. Min Act: -0.1700
Data Index: 1257571 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0767. Min Range: -2.0767
Max Act: 2.0599. Min Act: -0.1700
Data Index: 775801 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0767. Min Range: -2.0767
Max Act: 2.0094. Min Act: -0.1700
Data Index: 1336080 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9925. Min Act: -0.1700
Data Index: 893133 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9587. Min Act: -0.1700
Data Index: 825798 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9756. Min Act: -0.1700
Data Index: 21728 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9756. Min Act: -0.1700
Data Index: 383441 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9925. Min Act: -0.1700
Data Index: 453318 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9756. Min Act: -0.1700
Data Index: 104469 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9756. Min Act: -0.1700
Data Index: 203268 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9756. Min Act: -0.1700
Data Index: 966607 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9587. Min Act: -0.1700
Data Index: 827682 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9587. Min Act: -0.1700
Data Index: 379484 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9587. Min Act: -0.1700
Data Index: 740384 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9247. Min Act: -0.1700
Data Index: 53939 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9417. Min Act: -0.1700
Data Index: 736278 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9417. Min Act: -0.1700
Data Index: 111620 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9247. Min Act: -0.1700
Data Index: 849624 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9417. Min Act: -0.1700
Data Index: 97192 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0767. Min Range: -2.0767
Max Act: 1.9417. Min Act: -0.1700
Data Index: 456405 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19