Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 868 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.7874. Min Act: -0.1700
Data Index: 896608 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.6155. Min Act: -0.1700
Data Index: 11065 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.5998. Min Act: -0.1700
Data Index: 548604 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.5373. Min Act: -0.1700
Data Index: 1005747 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.5686. Min Act: -0.1700
Data Index: 660768 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.5530. Min Act: -0.1700
Data Index: 351762 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.4748. Min Act: -0.1700
Data Index: 386784 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.4748. Min Act: -0.1700
Data Index: 608713 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.4280. Min Act: -0.1700
Data Index: 1265463 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.4280. Min Act: -0.1700
Data Index: 24497 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.4123. Min Act: -0.1700
Data Index: 1206939 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.4436. Min Act: -0.1700
Data Index: 988087 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.4123. Min Act: -0.1700
Data Index: 700166 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.3967. Min Act: -0.1700
Data Index: 430906 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.3967. Min Act: -0.1700
Data Index: 316483 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.4123. Min Act: -0.1700
Data Index: 974047 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.3967. Min Act: -0.1700
Data Index: 1281013 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.3967. Min Act: -0.1700
Data Index: 317160 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.3967. Min Act: -0.1700
Data Index: 364673 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7874. Min Range: -4.7874
Max Act: 4.4123. Min Act: -0.1700
Data Index: 407532 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19