Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3738 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.1760. Min Act: -0.1700
Data Index: 3450223 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.1260. Min Act: -0.1700
Data Index: 8659508 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0590. Min Act: -0.1700
Data Index: 7901252 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0422. Min Act: -0.1700
Data Index: 6171737 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0422. Min Act: -0.1700
Data Index: 3394582 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0422. Min Act: -0.1700
Data Index: 7548507 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0422. Min Act: -0.1700
Data Index: 356273 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0422. Min Act: -0.1700
Data Index: 1258933 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0169. Min Act: -0.1700
Data Index: 7378740 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0253. Min Act: -0.1700
Data Index: 8569780 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0253. Min Act: -0.1700
Data Index: 833527 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0253. Min Act: -0.1700
Data Index: 751010 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0253. Min Act: -0.1700
Data Index: 1654513 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0422. Min Act: -0.1700
Data Index: 368024 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0253. Min Act: -0.1700
Data Index: 8701587 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0253. Min Act: -0.1700
Data Index: 1353048 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0169. Min Act: -0.1700
Data Index: 1143188 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0253. Min Act: -0.1700
Data Index: 1703621 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0253. Min Act: -0.1700
Data Index: 1738630 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1760. Min Range: -2.1760
Max Act: 2.0169. Min Act: -0.1700
Data Index: 6115459 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19