Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.8211. Min Act: -0.1700
Data Index: 4798836 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.6023. Min Act: -0.1700
Data Index: 6813164 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.5711. Min Act: -0.1700
Data Index: 928495 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.5398. Min Act: -0.1700
Data Index: 3175846 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.5711. Min Act: -0.1700
Data Index: 8196451 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.5086. Min Act: -0.1700
Data Index: 455010 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.5711. Min Act: -0.1700
Data Index: 8625598 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.5398. Min Act: -0.1700
Data Index: 3757804 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.5398. Min Act: -0.1700
Data Index: 4179341 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.5086. Min Act: -0.1700
Data Index: 3195548 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4773. Min Act: -0.1700
Data Index: 2247126 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4773. Min Act: -0.1700
Data Index: 5790308 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4773. Min Act: -0.1700
Data Index: 4416548 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4773. Min Act: -0.1700
Data Index: 2776148 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4461. Min Act: -0.1700
Data Index: 2760231 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4461. Min Act: -0.1700
Data Index: 768611 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4773. Min Act: -0.1700
Data Index: 3601823 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4148. Min Act: -0.1700
Data Index: 3854445 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4148. Min Act: -0.1700
Data Index: 4775013 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8211. Min Range: -4.8211
Max Act: 4.4148. Min Act: -0.1700
Data Index: 1743967 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19