Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1650 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.6043. Min Act: -0.1700
Data Index: 427726 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.5882. Min Act: -0.1700
Data Index: 1145815 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.5882. Min Act: -0.1700
Data Index: 305277 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.5399. Min Act: -0.1700
Data Index: 737934 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.5237. Min Act: -0.1700
Data Index: 1050982 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.5075. Min Act: -0.1700
Data Index: 184157 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.4751. Min Act: -0.1700
Data Index: 422054 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.4589. Min Act: -0.1700
Data Index: 35478 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.4263. Min Act: -0.1700
Data Index: 1261744 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.4101. Min Act: -0.1700
Data Index: 1345757 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.3937. Min Act: -0.1700
Data Index: 677987 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.3937. Min Act: -0.1700
Data Index: 573354 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.4101. Min Act: -0.1700
Data Index: 827129 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.3937. Min Act: -0.1700
Data Index: 267644 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.3937. Min Act: -0.1700
Data Index: 355354 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.3937. Min Act: -0.1700
Data Index: 1342123 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.3774. Min Act: -0.1700
Data Index: 720335 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.3937. Min Act: -0.1700
Data Index: 477265 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.4101. Min Act: -0.1700
Data Index: 461042 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6043. Min Range: -2.6043
Max Act: 2.3937. Min Act: -0.1700
Data Index: 232878 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19