Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 36 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4945. Min Act: -0.1700
Data Index: 194165 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4945. Min Act: -0.1700
Data Index: 342559 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4295. Min Act: -0.1700
Data Index: 142084 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4295. Min Act: -0.1700
Data Index: 991650 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4295. Min Act: -0.1700
Data Index: 784193 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4295. Min Act: -0.1700
Data Index: 615375 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4295. Min Act: -0.1700
Data Index: 474045 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3969. Min Act: -0.1700
Data Index: 1018050 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4132. Min Act: -0.1700
Data Index: 940099 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4132. Min Act: -0.1700
Data Index: 1129193 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.4132. Min Act: -0.1700
Data Index: 1082464 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3969. Min Act: -0.1700
Data Index: 1169907 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3806. Min Act: -0.1700
Data Index: 74294 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3969. Min Act: -0.1700
Data Index: 118390 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3969. Min Act: -0.1700
Data Index: 928821 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3969. Min Act: -0.1700
Data Index: 872408 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3806. Min Act: -0.1700
Data Index: 601448 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3806. Min Act: -0.1700
Data Index: 227124 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3806. Min Act: -0.1700
Data Index: 717489 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4945. Min Range: -2.4945
Max Act: 2.3806. Min Act: -0.1700
Data Index: 451184 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19