Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.7487. Min Act: -0.1700
Data Index: 1795045 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.6550. Min Act: -0.1700
Data Index: 383060 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.6862. Min Act: -0.1700
Data Index: 3205970 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.6550. Min Act: -0.1700
Data Index: 8081271 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.6237. Min Act: -0.1700
Data Index: 4637127 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.6237. Min Act: -0.1700
Data Index: 6539991 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.5612. Min Act: -0.1700
Data Index: 7400556 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.5612. Min Act: -0.1700
Data Index: 2608053 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.5925. Min Act: -0.1700
Data Index: 8100974 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.5612. Min Act: -0.1700
Data Index: 3269739 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.5612. Min Act: -0.1700
Data Index: 8329569 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.5925. Min Act: -0.1700
Data Index: 1961430 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.4987. Min Act: -0.1700
Data Index: 395264 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.5612. Min Act: -0.1700
Data Index: 8801537 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.4987. Min Act: -0.1700
Data Index: 7171146 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.5299. Min Act: -0.1700
Data Index: 6903585 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.4674. Min Act: -0.1700
Data Index: 5174094 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.4674. Min Act: -0.1700
Data Index: 6721709 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.4362. Min Act: -0.1698
Data Index: 7048437 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7487. Min Range: -4.7487
Max Act: 4.4674. Min Act: -0.1700
Data Index: 6322350 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19