Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.4841. Min Act: -0.1700
Data Index: 7833231 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.2341. Min Act: -0.1693
Data Index: 7977789 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.1716. Min Act: -0.1699
Data Index: 6652772 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.1091. Min Act: -0.1468
Data Index: 7567569 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.0778. Min Act: -0.1664
Data Index: 8675752 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.0466. Min Act: -0.1693
Data Index: 7095813 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.0778. Min Act: -0.1298
Data Index: 5167766 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.0466. Min Act: -0.0580
Data Index: 6335890 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.0153. Min Act: -0.1698
Data Index: 7095814 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4841. Min Range: -6.4841
Max Act: 6.0153. Min Act: -0.1691
Data Index: 4399932 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.9841. Min Act: -0.0176
Data Index: 957505 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.9528. Min Act: -0.1698
Data Index: 7977780 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.9216. Min Act: -0.1700
Data Index: 4035766 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.9216. Min Act: -0.1700
Data Index: 7927175 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.9216. Min Act: -0.1700
Data Index: 1967383 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.9216. Min Act: -0.1700
Data Index: 4101265 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.9216. Min Act: -0.1676
Data Index: 4899379 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.9216. Min Act: -0.1699
Data Index: 7977794 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.8903. Min Act: -0.1406
Data Index: 4799859 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4841. Min Range: -6.4841
Max Act: 5.8903. Min Act: -0.1700
Data Index: 2150651 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19