Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 507 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.8707. Min Act: -0.1700
Data Index: 3044582 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.8707. Min Act: -0.1700
Data Index: 4795717 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.8394. Min Act: -0.1700
Data Index: 1264319 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.7769. Min Act: -0.1700
Data Index: 2561909 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.7144. Min Act: -0.1700
Data Index: 4795718 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.6519. Min Act: -0.1700
Data Index: 2687046 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.6207. Min Act: -0.1700
Data Index: 1146742 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.6832. Min Act: -0.1700
Data Index: 6613169 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.5894. Min Act: -0.1700
Data Index: 87140 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.5269. Min Act: -0.1700
Data Index: 6299582 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.4644. Min Act: -0.1700
Data Index: 7156089 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.4644. Min Act: -0.1700
Data Index: 5924067 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.4332. Min Act: -0.1700
Data Index: 895152 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.4332. Min Act: -0.1700
Data Index: 1584718 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.4019. Min Act: -0.1700
Data Index: 6656236 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.4019. Min Act: -0.1700
Data Index: 4173706 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.4019. Min Act: -0.1700
Data Index: 5284729 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.3394. Min Act: -0.1700
Data Index: 3400104 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.3394. Min Act: -0.1700
Data Index: 3984199 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8707. Min Range: -5.8707
Max Act: 5.3394. Min Act: -0.1700
Data Index: 1076838 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19