Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 586 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.5201. Min Act: -0.1700
Data Index: 1522222 (Python Code)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.4715. Min Act: -0.1700
Data Index: 1383517 (Python Code)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.4390. Min Act: -0.1700
Data Index: 1616681 (Python Code)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.4227. Min Act: -0.1700
Data Index: 1482001 (Python Code)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.4227. Min Act: -0.1700
Data Index: 1500700 (Python Code)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.4227. Min Act: -0.1700
Data Index: 1489154 (Python Code)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.4064. Min Act: -0.1700
Data Index: 1506944 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3737. Min Act: -0.1700
Data Index: 1021048 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3901. Min Act: -0.1700
Data Index: 1402844 (Python Code)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3737. Min Act: -0.1700
Data Index: 433922 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3737. Min Act: -0.1700
Data Index: 1545980 (Python Code)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3737. Min Act: -0.1700
Data Index: 1406952 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3737. Min Act: -0.1700
Data Index: 1649465 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3737. Min Act: -0.1700
Data Index: 1619126 (Python Code)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3737. Min Act: -0.1700
Data Index: 1414651 (Python Code)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3574. Min Act: -0.1700
Data Index: 1517416 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3410. Min Act: -0.1700
Data Index: 1589818 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3410. Min Act: -0.1700
Data Index: 1589512 (Python Code)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3410. Min Act: -0.1700
Data Index: 1362985 (Python Code)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5201. Min Range: -2.5201
Max Act: 2.3410. Min Act: -0.1700
Data Index: 608827 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19