Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 144 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.4092. Min Act: -0.1432
Data Index: 1111099 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.3275. Min Act: -0.1700
Data Index: 34057 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.2617. Min Act: -0.1474
Data Index: 180223 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.2286. Min Act: -0.1335
Data Index: 1003472 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.2121. Min Act: -0.1567
Data Index: 172241 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.2121. Min Act: -0.1498
Data Index: 1025823 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.2121. Min Act: -0.1636
Data Index: 1098477 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1955. Min Act: -0.1507
Data Index: 1213837 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1955. Min Act: -0.1673
Data Index: 1079767 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.2121. Min Act: -0.1660
Data Index: 560897 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1789. Min Act: -0.1352
Data Index: 1535139 (Python Code)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1789. Min Act: -0.1700
Data Index: 882082 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1789. Min Act: -0.1459
Data Index: 1230659 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1623. Min Act: -0.1683
Data Index: 1017796 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1623. Min Act: -0.1242
Data Index: 5754 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1789. Min Act: -0.1439
Data Index: 1505447 (Python Code)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1789. Min Act: -0.1394
Data Index: 549887 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1456. Min Act: -0.1638
Data Index: 145778 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1456. Min Act: -0.1700
Data Index: 1236159 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4092. Min Range: -2.4092
Max Act: 2.1456. Min Act: -0.1578
Data Index: 1332962 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19