Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 215 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.4506. Min Act: -0.1700
Data Index: 722152 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.4180. Min Act: -0.1700
Data Index: 305595 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.4017. Min Act: -0.1700
Data Index: 895522 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3854. Min Act: -0.1700
Data Index: 1132831 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3691. Min Act: -0.1700
Data Index: 964540 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3527. Min Act: -0.1700
Data Index: 67774 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3363. Min Act: -0.1700
Data Index: 667380 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3363. Min Act: -0.1700
Data Index: 203559 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3363. Min Act: -0.1700
Data Index: 1096584 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3199. Min Act: -0.1700
Data Index: 1135583 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3199. Min Act: -0.1700
Data Index: 934371 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3199. Min Act: -0.1700
Data Index: 378247 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3199. Min Act: -0.1700
Data Index: 1171522 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3035. Min Act: -0.1700
Data Index: 1337754 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.2871. Min Act: -0.1700
Data Index: 832732 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3035. Min Act: -0.1700
Data Index: 363204 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.3035. Min Act: -0.1700
Data Index: 1085771 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.2871. Min Act: -0.1700
Data Index: 972160 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.2871. Min Act: -0.1700
Data Index: 998842 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4506. Min Range: -2.4506
Max Act: 2.2871. Min Act: -0.1700
Data Index: 1196807 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19