Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1578 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.6934. Min Act: -0.1700
Data Index: 5412097 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.6308. Min Act: -0.1700
Data Index: 5896039 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.6152. Min Act: -0.1700
Data Index: 7151130 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.5839. Min Act: -0.1700
Data Index: 4523306 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.4116. Min Act: -0.1700
Data Index: 92228 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.4116. Min Act: -0.1700
Data Index: 5159926 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.3802. Min Act: -0.1700
Data Index: 7434455 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.3332. Min Act: -0.1700
Data Index: 7383495 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.3175. Min Act: -0.1700
Data Index: 8369787 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2861. Min Act: -0.1700
Data Index: 6742860 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2861. Min Act: -0.1700
Data Index: 2160312 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2704. Min Act: -0.1700
Data Index: 7844156 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2861. Min Act: -0.1700
Data Index: 3393619 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2389. Min Act: -0.1700
Data Index: 1534094 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2389. Min Act: -0.1700
Data Index: 4262619 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2389. Min Act: -0.1700
Data Index: 5229593 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2547. Min Act: -0.1700
Data Index: 8269991 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2232. Min Act: -0.1700
Data Index: 2328962 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2389. Min Act: -0.1700
Data Index: 7528329 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6934. Min Range: -3.6934
Max Act: 3.2389. Min Act: -0.1700
Data Index: 4445846 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19