Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1967. Min Range: -3.1967
Max Act: 3.1967. Min Act: -0.1700
Data Index: 2302568 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1967. Min Range: -3.1967
Max Act: 3.0864. Min Act: -0.1700
Data Index: 4694003 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1967. Min Range: -3.1967
Max Act: 3.0707. Min Act: -0.1700
Data Index: 8526925 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1967. Min Range: -3.1967
Max Act: 3.0391. Min Act: -0.1700
Data Index: 3124289 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.9759. Min Act: -0.1700
Data Index: 2636357 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.9759. Min Act: -0.1700
Data Index: 8802016 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.9443. Min Act: -0.1700
Data Index: 245266 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.9601. Min Act: -0.1700
Data Index: 6230337 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.9443. Min Act: -0.1700
Data Index: 7291948 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.9284. Min Act: -0.1700
Data Index: 2694648 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8809. Min Act: -0.1700
Data Index: 5080816 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8967. Min Act: -0.1700
Data Index: 1642592 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8650. Min Act: -0.1700
Data Index: 3280444 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8650. Min Act: -0.1700
Data Index: 3550570 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8332. Min Act: -0.1700
Data Index: 8024777 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8491. Min Act: -0.1700
Data Index: 5345323 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8173. Min Act: -0.1700
Data Index: 6203897 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8014. Min Act: -0.1700
Data Index: 550197 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8332. Min Act: -0.1700
Data Index: 6567921 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1967. Min Range: -3.1967
Max Act: 2.8491. Min Act: -0.1700
Data Index: 5567661 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19