Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 28 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0898. Min Range: -3.0898
Max Act: 3.0898. Min Act: -0.1700
Data Index: 819403 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0898. Min Range: -3.0898
Max Act: 3.0267. Min Act: -0.1700
Data Index: 232841 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.9951. Min Act: -0.1700
Data Index: 533714 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.9793. Min Act: -0.1700
Data Index: 1040578 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.9159. Min Act: -0.1700
Data Index: 1335228 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.9159. Min Act: -0.1700
Data Index: 1268226 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.9159. Min Act: -0.1700
Data Index: 1247469 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8842. Min Act: -0.1700
Data Index: 163203 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.9001. Min Act: -0.1700
Data Index: 130956 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8683. Min Act: -0.1700
Data Index: 980440 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8683. Min Act: -0.1700
Data Index: 1103500 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8524. Min Act: -0.1700
Data Index: 230261 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8683. Min Act: -0.1700
Data Index: 791329 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8524. Min Act: -0.1700
Data Index: 603418 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8683. Min Act: -0.1700
Data Index: 114097 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8524. Min Act: -0.1700
Data Index: 1087075 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8842. Min Act: -0.1700
Data Index: 236376 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8365. Min Act: -0.1700
Data Index: 636248 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8683. Min Act: -0.1700
Data Index: 942072 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0898. Min Range: -3.0898
Max Act: 2.8524. Min Act: -0.1700
Data Index: 992973 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19