Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.3659. Min Act: -0.1700
Data Index: 3558017 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.2409. Min Act: -0.1700
Data Index: 3743635 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.1159. Min Act: -0.1700
Data Index: 2093421 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.1159. Min Act: -0.1700
Data Index: 7858602 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.1159. Min Act: -0.1700
Data Index: 5896830 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.1159. Min Act: -0.1700
Data Index: 3143751 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.0534. Min Act: -0.1700
Data Index: 2750807 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.0847. Min Act: -0.1700
Data Index: 3911373 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.0534. Min Act: -0.1700
Data Index: 6214805 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.0847. Min Act: -0.1700
Data Index: 5178574 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.0534. Min Act: -0.1700
Data Index: 7471940 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.0222. Min Act: -0.1700
Data Index: 8715228 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3659. Min Range: -7.3659
Max Act: 7.0222. Min Act: -0.1700
Data Index: 5823312 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3659. Min Range: -7.3659
Max Act: 6.9597. Min Act: -0.1700
Data Index: 6091641 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3659. Min Range: -7.3659
Max Act: 6.9597. Min Act: -0.1700
Data Index: 637594 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3659. Min Range: -7.3659
Max Act: 6.9597. Min Act: -0.1700
Data Index: 1022075 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3659. Min Range: -7.3659
Max Act: 6.9597. Min Act: -0.1700
Data Index: 8003407 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3659. Min Range: -7.3659
Max Act: 6.9284. Min Act: -0.1700
Data Index: 6047600 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3659. Min Range: -7.3659
Max Act: 6.9284. Min Act: -0.1700
Data Index: 4243202 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3659. Min Range: -7.3659
Max Act: 6.9284. Min Act: -0.1700
Data Index: 5486141 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19