Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 604 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4867. Min Act: -0.1700
Data Index: 1310625 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4542. Min Act: -0.1700
Data Index: 1572876 (Python Code)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4380. Min Act: -0.1700
Data Index: 1346324 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4542. Min Act: -0.1700
Data Index: 230455 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4542. Min Act: -0.1700
Data Index: 337932 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4542. Min Act: -0.1700
Data Index: 647000 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4542. Min Act: -0.1700
Data Index: 904263 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4542. Min Act: -0.1700
Data Index: 1214350 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4542. Min Act: -0.1700
Data Index: 694816 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4380. Min Act: -0.1700
Data Index: 763923 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4542. Min Act: -0.1700
Data Index: 1178756 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4380. Min Act: -0.1700
Data Index: 1424055 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4217. Min Act: -0.1700
Data Index: 202919 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4217. Min Act: -0.1700
Data Index: 463265 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4217. Min Act: -0.1700
Data Index: 282712 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4217. Min Act: -0.1700
Data Index: 691151 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4217. Min Act: -0.1700
Data Index: 580484 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4217. Min Act: -0.1700
Data Index: 504425 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.4054. Min Act: -0.1700
Data Index: 1402631 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4867. Min Range: -2.4867
Max Act: 2.3891. Min Act: -0.1700
Data Index: 1517966 (Python Code)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19