Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1810 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2690. Min Range: -2.2690
Max Act: 2.2690. Min Act: -0.1700
Data Index: 316098 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2690. Min Range: -2.2690
Max Act: 2.1697. Min Act: -0.1700
Data Index: 1005597 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2690. Min Range: -2.2690
Max Act: 2.1531. Min Act: -0.1699
Data Index: 863830 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2690. Min Range: -2.2690
Max Act: 2.0443. Min Act: -0.1700
Data Index: 453756 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2690. Min Range: -2.2690
Max Act: 2.0443. Min Act: -0.1700
Data Index: 1294830 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2690. Min Range: -2.2690
Max Act: 2.0190. Min Act: -0.1699
Data Index: 195365 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2690. Min Range: -2.2690
Max Act: 2.0106. Min Act: -0.1700
Data Index: 907710 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.9683. Min Act: -0.1699
Data Index: 473500 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.9514. Min Act: -0.1700
Data Index: 844218 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.9429. Min Act: -0.1700
Data Index: 364201 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.9259. Min Act: -0.1700
Data Index: 1168886 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.9004. Min Act: -0.1700
Data Index: 1142355 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.9089. Min Act: -0.1700
Data Index: 888055 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.8833. Min Act: -0.1700
Data Index: 745656 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.8833. Min Act: -0.1699
Data Index: 307650 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.8663. Min Act: -0.1700
Data Index: 144864 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.8406. Min Act: -0.1700
Data Index: 75250 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.8406. Min Act: -0.1700
Data Index: 1075877 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.8406. Min Act: -0.1700
Data Index: 493178 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2690. Min Range: -2.2690
Max Act: 1.8149. Min Act: -0.1700
Data Index: 1090938 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19