Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 166 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.6915. Min Act: -0.1700
Data Index: 608837 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5952. Min Act: -0.1700
Data Index: 50598 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.6113. Min Act: -0.1700
Data Index: 280975 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5952. Min Act: -0.1700
Data Index: 346560 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5791. Min Act: -0.1700
Data Index: 995072 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5791. Min Act: -0.1700
Data Index: 675980 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5791. Min Act: -0.1700
Data Index: 517843 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5630. Min Act: -0.1700
Data Index: 566675 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5630. Min Act: -0.1700
Data Index: 310002 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5630. Min Act: -0.1700
Data Index: 573714 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5630. Min Act: -0.1700
Data Index: 771297 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5468. Min Act: -0.1700
Data Index: 556427 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5468. Min Act: -0.1700
Data Index: 530793 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5630. Min Act: -0.1700
Data Index: 561261 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5468. Min Act: -0.1700
Data Index: 131961 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5468. Min Act: -0.1700
Data Index: 646335 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5307. Min Act: -0.1700
Data Index: 352120 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5307. Min Act: -0.1700
Data Index: 481552 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5307. Min Act: -0.1700
Data Index: 520665 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6915. Min Range: -2.6915
Max Act: 2.5307. Min Act: -0.1700
Data Index: 133237 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19