Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1930 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.7577. Min Act: -0.1700
Data Index: 547326 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5814. Min Act: -0.1700
Data Index: 958291 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5491. Min Act: -0.1700
Data Index: 3736 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.5168. Min Act: -0.1700
Data Index: 55800 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4844. Min Act: -0.1700
Data Index: 508780 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4682. Min Act: -0.1700
Data Index: 1023668 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4520. Min Act: -0.1700
Data Index: 1316072 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4520. Min Act: -0.1700
Data Index: 506930 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4520. Min Act: -0.1700
Data Index: 242516 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4682. Min Act: -0.1700
Data Index: 882382 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4357. Min Act: -0.1700
Data Index: 289270 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4520. Min Act: -0.1700
Data Index: 177417 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4194. Min Act: -0.1700
Data Index: 994106 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4194. Min Act: -0.1700
Data Index: 1132144 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4194. Min Act: -0.1700
Data Index: 1295136 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4194. Min Act: -0.1700
Data Index: 971266 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.3868. Min Act: -0.1700
Data Index: 162590 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4031. Min Act: -0.1700
Data Index: 314829 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.4194. Min Act: -0.1700
Data Index: 335817 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7577. Min Range: -2.7577
Max Act: 2.3868. Min Act: -0.1700
Data Index: 1007449 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19