Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3154 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0841. Min Act: -0.1620
Data Index: 6555396 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0793. Min Act: -0.1526
Data Index: 8110097 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0338. Min Act: -0.1688
Data Index: 7793779 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0295. Min Act: -0.1614
Data Index: 7233358 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0211. Min Act: -0.1693
Data Index: 2064618 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0211. Min Act: -0.1506
Data Index: 8685226 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0211. Min Act: -0.1257
Data Index: 2177885 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0129. Min Act: -0.1697
Data Index: 5897215 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0088. Min Act: -0.1698
Data Index: 3772157 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0048. Min Act: -0.1313
Data Index: 3418143 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0048. Min Act: -0.1669
Data Index: 583712 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0841. Min Range: -0.0841
Max Act: 0.0048. Min Act: -0.1698
Data Index: 8744525 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0841. Min Range: -0.0841
Max Act: -0.0000. Min Act: -0.1361
Data Index: 10 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0841. Min Range: -0.0841
Max Act: -0.0000. Min Act: -0.1662
Data Index: 19 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0841. Min Range: -0.0841
Max Act: -0.0000. Min Act: -0.1215
Data Index: 25 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0841. Min Range: -0.0841
Max Act: -0.0000. Min Act: -0.1590
Data Index: 24 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0841. Min Range: -0.0841
Max Act: -0.0000. Min Act: -0.1484
Data Index: 17 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0841. Min Range: -0.0841
Max Act: -0.0000. Min Act: -0.1320
Data Index: 21 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0841. Min Range: -0.0841
Max Act: -0.0000. Min Act: -0.1461
Data Index: 20 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0841. Min Range: -0.0841
Max Act: -0.0000. Min Act: -0.1646
Data Index: 22 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19