Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1411 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.2147. Min Act: -0.1700
Data Index: 296737 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.1815. Min Act: -0.1700
Data Index: 502686 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.1483. Min Act: -0.1700
Data Index: 1088002 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.1316. Min Act: -0.1700
Data Index: 988991 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.1316. Min Act: -0.1700
Data Index: 968960 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.1149. Min Act: -0.1700
Data Index: 423851 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.1316. Min Act: -0.1700
Data Index: 582994 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.1316. Min Act: -0.1700
Data Index: 872357 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0982. Min Act: -0.1700
Data Index: 546118 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0814. Min Act: -0.1700
Data Index: 1026190 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0814. Min Act: -0.1700
Data Index: 228851 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0982. Min Act: -0.1700
Data Index: 1140536 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0814. Min Act: -0.1700
Data Index: 790441 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0814. Min Act: -0.1700
Data Index: 804448 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0647. Min Act: -0.1700
Data Index: 1017843 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0814. Min Act: -0.1700
Data Index: 833004 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0647. Min Act: -0.1700
Data Index: 860151 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0647. Min Act: -0.1700
Data Index: 678831 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0814. Min Act: -0.1700
Data Index: 479134 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2147. Min Range: -2.2147
Max Act: 2.0647. Min Act: -0.1700
Data Index: 757423 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19