Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2038 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.5194. Min Act: -0.1700
Data Index: 969271 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.5032. Min Act: -0.1700
Data Index: 1442973 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.5032. Min Act: -0.1700
Data Index: 75580 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4545. Min Act: -0.1700
Data Index: 1645594 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4545. Min Act: -0.1700
Data Index: 1612881 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4545. Min Act: -0.1700
Data Index: 312743 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4383. Min Act: -0.1700
Data Index: 781975 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4057. Min Act: -0.1700
Data Index: 1397496 (Python Code)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4220. Min Act: -0.1700
Data Index: 1494616 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4383. Min Act: -0.1700
Data Index: 226979 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4383. Min Act: -0.1700
Data Index: 581379 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4057. Min Act: -0.1700
Data Index: 1524265 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4057. Min Act: -0.1700
Data Index: 1503809 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.3894. Min Act: -0.1700
Data Index: 1632428 (Python Code)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4057. Min Act: -0.1700
Data Index: 1653322 (Python Code)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.3894. Min Act: -0.1700
Data Index: 1527806 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.3731. Min Act: -0.1700
Data Index: 1629217 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.4057. Min Act: -0.1700
Data Index: 102116 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.3894. Min Act: -0.1700
Data Index: 1441568 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5194. Min Range: -2.5194
Max Act: 2.3894. Min Act: -0.1700
Data Index: 1601344 (Python Code)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19