Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 939 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.3983. Min Act: -0.1700
Data Index: 1264788 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.3820. Min Act: -0.1700
Data Index: 1655146 (Python Code)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2836. Min Act: -0.1700
Data Index: 430046 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.3001. Min Act: -0.1700
Data Index: 1471882 (Python Code)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2836. Min Act: -0.1700
Data Index: 173466 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2672. Min Act: -0.1700
Data Index: 1478973 (Python Code)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2672. Min Act: -0.1700
Data Index: 1273353 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2672. Min Act: -0.1700
Data Index: 753585 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2507. Min Act: -0.1700
Data Index: 1490210 (Python Code)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2341. Min Act: -0.1700
Data Index: 1033441 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2176. Min Act: -0.1700
Data Index: 1355389 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2176. Min Act: -0.1700
Data Index: 547781 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2176. Min Act: -0.1700
Data Index: 1368445 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2341. Min Act: -0.1700
Data Index: 1522322 (Python Code)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2176. Min Act: -0.1700
Data Index: 58114 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2176. Min Act: -0.1700
Data Index: 743007 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2010. Min Act: -0.1700
Data Index: 216682 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.1844. Min Act: -0.1700
Data Index: 870359 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2010. Min Act: -0.1700
Data Index: 1538347 (Python Code)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3983. Min Range: -2.3983
Max Act: 2.2010. Min Act: -0.1699
Data Index: 531819 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19