Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1914 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0633. Min Range: -4.0633
Max Act: 4.0633. Min Act: -0.1700
Data Index: 1518841 (Python Code)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0633. Min Range: -4.0633
Max Act: 4.0164. Min Act: -0.1700
Data Index: 1150578 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0633. Min Range: -4.0633
Max Act: 4.0164. Min Act: -0.1700
Data Index: 60480 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.9226. Min Act: -0.1700
Data Index: 1262209 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8757. Min Act: -0.1700
Data Index: 768118 (C4 (Web Text))
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.9070. Min Act: -0.1700
Data Index: 1239353 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8757. Min Act: -0.1700
Data Index: 150600 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8601. Min Act: -0.1700
Data Index: 699596 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8601. Min Act: -0.1700
Data Index: 927293 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8445. Min Act: -0.1700
Data Index: 363013 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8132. Min Act: -0.1700
Data Index: 1641144 (Python Code)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8601. Min Act: -0.1700
Data Index: 547700 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.9070. Min Act: -0.1700
Data Index: 665306 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8288. Min Act: -0.1700
Data Index: 1152927 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.7975. Min Act: -0.1700
Data Index: 318341 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.7662. Min Act: -0.1700
Data Index: 1428493 (Python Code)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8914. Min Act: -0.1700
Data Index: 1377577 (Python Code)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.7506. Min Act: -0.1700
Data Index: 1271648 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8288. Min Act: -0.1700
Data Index: 314093 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0633. Min Range: -4.0633
Max Act: 3.8132. Min Act: -0.1700
Data Index: 1407441 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19