Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4319. Min Range: -6.4319
Max Act: 6.4319. Min Act: -0.1700
Data Index: 8725303 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4319. Min Range: -6.4319
Max Act: 6.2757. Min Act: -0.1700
Data Index: 1117452 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4319. Min Range: -6.4319
Max Act: 6.2132. Min Act: -0.1700
Data Index: 8290034 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4319. Min Range: -6.4319
Max Act: 6.1507. Min Act: -0.1700
Data Index: 1688009 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4319. Min Range: -6.4319
Max Act: 6.1194. Min Act: -0.1700
Data Index: 329916 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4319. Min Range: -6.4319
Max Act: 6.0569. Min Act: -0.1700
Data Index: 6778589 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4319. Min Range: -6.4319
Max Act: 6.0569. Min Act: -0.1700
Data Index: 5670094 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4319. Min Range: -6.4319
Max Act: 6.0257. Min Act: -0.1700
Data Index: 954081 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4319. Min Range: -6.4319
Max Act: 6.0257. Min Act: -0.1700
Data Index: 4585223 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.9944. Min Act: -0.1700
Data Index: 1646002 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.9944. Min Act: -0.1700
Data Index: 1688002 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.9944. Min Act: -0.1700
Data Index: 5542530 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.9319. Min Act: -0.1700
Data Index: 6152337 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.9632. Min Act: -0.1700
Data Index: 8758344 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.9319. Min Act: -0.1700
Data Index: 7895992 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.9319. Min Act: -0.1700
Data Index: 1894086 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.9319. Min Act: -0.1700
Data Index: 6471487 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.8694. Min Act: -0.1700
Data Index: 4159249 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.9319. Min Act: -0.1700
Data Index: 247529 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4319. Min Range: -6.4319
Max Act: 5.8694. Min Act: -0.1700
Data Index: 1687999 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19