Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0167. Min Range: -6.0167
Max Act: 6.0167. Min Act: -0.1700
Data Index: 7984063 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.9855. Min Act: -0.1700
Data Index: 4031303 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1624867 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.8292. Min Act: -0.1700
Data Index: 8588436 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.8292. Min Act: -0.1700
Data Index: 8585708 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.8292. Min Act: -0.1700
Data Index: 6781333 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.8292. Min Act: -0.1700
Data Index: 5122614 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.7980. Min Act: -0.1700
Data Index: 3989573 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.7355. Min Act: -0.1700
Data Index: 7465868 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.7355. Min Act: -0.1700
Data Index: 3238213 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.7355. Min Act: -0.1700
Data Index: 2422390 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.7042. Min Act: -0.1700
Data Index: 7460848 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.6730. Min Act: -0.1700
Data Index: 4833788 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.6730. Min Act: -0.1700
Data Index: 4618562 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.6730. Min Act: -0.1700
Data Index: 3329283 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.6730. Min Act: -0.1700
Data Index: 1727807 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.6730. Min Act: -0.1700
Data Index: 4373188 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.7042. Min Act: -0.1700
Data Index: 1698179 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.6730. Min Act: -0.1700
Data Index: 5698080 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0167. Min Range: -6.0167
Max Act: 5.6417. Min Act: -0.1700
Data Index: 7455635 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19