Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2045 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.7307. Min Act: -0.1700
Data Index: 91956 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6667. Min Act: -0.1700
Data Index: 374086 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6827. Min Act: -0.1700
Data Index: 745999 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6987. Min Act: -0.1700
Data Index: 1020472 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6987. Min Act: -0.1699
Data Index: 373460 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6827. Min Act: -0.1700
Data Index: 200007 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6667. Min Act: -0.1700
Data Index: 105266 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6827. Min Act: -0.1700
Data Index: 873091 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6667. Min Act: -0.1700
Data Index: 569618 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6506. Min Act: -0.1700
Data Index: 362021 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6506. Min Act: -0.1700
Data Index: 4185 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6506. Min Act: -0.1700
Data Index: 299985 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6506. Min Act: -0.1700
Data Index: 1086985 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6346. Min Act: -0.1700
Data Index: 1019579 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6506. Min Act: -0.1700
Data Index: 272218 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6506. Min Act: -0.1700
Data Index: 684695 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6024. Min Act: -0.1700
Data Index: 881598 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6185. Min Act: -0.1700
Data Index: 633179 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6024. Min Act: -0.1700
Data Index: 571488 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7307. Min Range: -2.7307
Max Act: 2.6185. Min Act: -0.1700
Data Index: 740793 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19