Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1250 in Layer 0
Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')
Click the toggle to see the full text!
Text #0
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.2011. Min Act: -0.1700
Data Index: 3380182 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1771. Min Act: -0.1700
Data Index: 1272900 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1634. Min Act: -0.1700
Data Index: 8543222 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1440. Min Act: -0.1700
Data Index: 2154165 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1535. Min Act: -0.1700
Data Index: 7620205 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1544. Min Act: -0.1700
Data Index: 7085994 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1337. Min Act: -0.1700
Data Index: 7907510 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1245. Min Act: -0.1700
Data Index: 8365586 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1297. Min Act: -0.1700
Data Index: 7597035 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1397. Min Act: -0.1700
Data Index: 3906692 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1326. Min Act: -0.1700
Data Index: 7339489 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1321. Min Act: -0.1700
Data Index: 1513350 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1386. Min Act: -0.1700
Data Index: 594689 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1376. Min Act: -0.1700
Data Index: 6046787 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1273. Min Act: -0.1700
Data Index: 8528227 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1220. Min Act: -0.1700
Data Index: 7584864 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1208. Min Act: -0.1700
Data Index: 1622236 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1193. Min Act: -0.1700
Data Index: 3264204 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1096. Min Act: -0.1700
Data Index: 6974597 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.2011. Min Range: -3.2011
Max Act: 3.1244. Min Act: -0.1700
Data Index: 6171257 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full textTruncated
Full Text #19