Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4266. Min Range: -6.4266
Max Act: 6.4266. Min Act: -0.1700
Data Index: 6001474 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4266. Min Range: -6.4266
Max Act: 6.2391. Min Act: -0.1700
Data Index: 2494515 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4266. Min Range: -6.4266
Max Act: 6.0829. Min Act: -0.1700
Data Index: 6828150 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4266. Min Range: -6.4266
Max Act: 6.0829. Min Act: -0.1700
Data Index: 5739632 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4266. Min Range: -6.4266
Max Act: 6.0829. Min Act: -0.1700
Data Index: 3662895 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.9891. Min Act: -0.1700
Data Index: 5835549 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.9891. Min Act: -0.1700
Data Index: 506274 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8954. Min Act: -0.1700
Data Index: 7466005 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.9266. Min Act: -0.1700
Data Index: 8213977 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.9266. Min Act: -0.1700
Data Index: 399659 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.9266. Min Act: -0.1700
Data Index: 4385578 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8954. Min Act: -0.1700
Data Index: 6803307 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8954. Min Act: -0.1700
Data Index: 6955183 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8954. Min Act: -0.1700
Data Index: 2145945 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8641. Min Act: -0.1700
Data Index: 3675252 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8641. Min Act: -0.1700
Data Index: 3578662 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8641. Min Act: -0.1700
Data Index: 214079 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8641. Min Act: -0.1700
Data Index: 3135615 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8641. Min Act: -0.1700
Data Index: 5217797 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4266. Min Range: -6.4266
Max Act: 5.8641. Min Act: -0.1700
Data Index: 4483204 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19