Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0668. Min Range: -2.0668
Max Act: 2.0668. Min Act: -0.1700
Data Index: 7848864 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0668. Min Range: -2.0668
Max Act: 2.0163. Min Act: -0.1700
Data Index: 6393800 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9994. Min Act: -0.1700
Data Index: 882098 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9994. Min Act: -0.1700
Data Index: 1926581 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9994. Min Act: -0.1700
Data Index: 3671319 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9994. Min Act: -0.1700
Data Index: 1589202 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9994. Min Act: -0.1700
Data Index: 4958499 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9825. Min Act: -0.1699
Data Index: 5367669 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9656. Min Act: -0.1700
Data Index: 1124671 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9825. Min Act: -0.1698
Data Index: 6170565 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9994. Min Act: -0.1700
Data Index: 1171158 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9825. Min Act: -0.1699
Data Index: 6258321 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9656. Min Act: -0.1700
Data Index: 3818211 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9656. Min Act: -0.1699
Data Index: 2495115 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9486. Min Act: -0.1700
Data Index: 8085235 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9656. Min Act: -0.1700
Data Index: 7965731 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9656. Min Act: -0.1675
Data Index: 2123409 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9486. Min Act: -0.1700
Data Index: 6887083 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9656. Min Act: -0.1697
Data Index: 3743170 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0668. Min Range: -2.0668
Max Act: 1.9486. Min Act: -0.1700
Data Index: 2753325 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19