Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1294 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.9644. Min Act: -0.1700
Data Index: 3435581 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.9332. Min Act: -0.1700
Data Index: 2047075 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.9332. Min Act: -0.1700
Data Index: 5118353 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.8394. Min Act: -0.1700
Data Index: 1345290 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.7769. Min Act: -0.1700
Data Index: 2248088 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.7769. Min Act: -0.1700
Data Index: 4907025 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.8082. Min Act: -0.1700
Data Index: 687997 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.7769. Min Act: -0.1700
Data Index: 69617 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.6832. Min Act: -0.1700
Data Index: 8123527 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.6832. Min Act: -0.1700
Data Index: 8718782 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.6207. Min Act: -0.1700
Data Index: 3247612 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.6207. Min Act: -0.1700
Data Index: 6411948 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.6207. Min Act: -0.1700
Data Index: 7766064 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.5894. Min Act: -0.1700
Data Index: 7290515 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.5894. Min Act: -0.1700
Data Index: 7101088 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.5582. Min Act: -0.1700
Data Index: 515286 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.5582. Min Act: -0.1700
Data Index: 5393413 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.5582. Min Act: -0.1700
Data Index: 6182359 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.5269. Min Act: -0.1700
Data Index: 6904964 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9644. Min Range: -5.9644
Max Act: 5.5269. Min Act: -0.1700
Data Index: 8239241 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19