Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 746 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.4691. Min Act: -0.1700
Data Index: 1485827 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.4528. Min Act: -0.1700
Data Index: 1552657 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.4203. Min Act: -0.1700
Data Index: 1565375 (Python Code)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.4040. Min Act: -0.1700
Data Index: 1653864 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.4040. Min Act: -0.1700
Data Index: 1626106 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.4040. Min Act: -0.1700
Data Index: 1385373 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3877. Min Act: -0.1700
Data Index: 1464350 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3550. Min Act: -0.1700
Data Index: 1568354 (Python Code)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3222. Min Act: -0.1700
Data Index: 1574705 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3222. Min Act: -0.1700
Data Index: 1608985 (Python Code)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3386. Min Act: -0.1700
Data Index: 356805 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3058. Min Act: -0.1700
Data Index: 1023359 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3222. Min Act: -0.1700
Data Index: 1646984 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3058. Min Act: -0.1700
Data Index: 1627948 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3222. Min Act: -0.1700
Data Index: 1385881 (Python Code)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3058. Min Act: -0.1700
Data Index: 1432985 (Python Code)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3058. Min Act: -0.1700
Data Index: 1587813 (Python Code)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3222. Min Act: -0.1700
Data Index: 1419365 (Python Code)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3058. Min Act: -0.1700
Data Index: 1390460 (Python Code)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4691. Min Range: -2.4691
Max Act: 2.3058. Min Act: -0.1700
Data Index: 1536242 (Python Code)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19