Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1875 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.2064. Min Act: -0.1700
Data Index: 344734 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1898. Min Act: -0.1700
Data Index: 1202932 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1898. Min Act: -0.1700
Data Index: 716102 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1898. Min Act: -0.1700
Data Index: 186612 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1566. Min Act: -0.1700
Data Index: 1400844 (Python Code)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1399. Min Act: -0.1700
Data Index: 1353676 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 208063 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 472018 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1399. Min Act: -0.1700
Data Index: 1369101 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 1390167 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 1467581 (Python Code)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 1399589 (Python Code)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 1470218 (Python Code)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 1471709 (Python Code)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 756357 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 569616 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1232. Min Act: -0.1700
Data Index: 1155427 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1065. Min Act: -0.1700
Data Index: 1473930 (Python Code)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1065. Min Act: -0.1699
Data Index: 1505738 (Python Code)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2064. Min Range: -2.2064
Max Act: 2.1065. Min Act: -0.1700
Data Index: 1654110 (Python Code)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19