Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 485 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7475. Min Range: -6.7475
Max Act: 5.6225. Min Act: -0.1700
Data Index: 1879849 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5600. Min Act: -0.1700
Data Index: 708724 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7475. Min Range: -6.7475
Max Act: 5.4038. Min Act: -0.1700
Data Index: 3463470 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7475. Min Range: -6.7475
Max Act: 5.4038. Min Act: -0.1700
Data Index: 4539205 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.7475. Min Act: -0.1700
Data Index: 4797376 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5913. Min Act: -0.1700
Data Index: 6385498 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.6225. Min Act: -0.1700
Data Index: 108795 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5913. Min Act: -0.1700
Data Index: 8291049 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5913. Min Act: -0.1700
Data Index: 7399076 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5913. Min Act: -0.1700
Data Index: 6662604 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5288. Min Act: -0.1700
Data Index: 4148750 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5288. Min Act: -0.1700
Data Index: 8213421 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4975. Min Act: -0.1700
Data Index: 7508511 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4975. Min Act: -0.1700
Data Index: 6031300 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4975. Min Act: -0.1700
Data Index: 8076884 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4975. Min Act: -0.1700
Data Index: 2031184 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4663. Min Act: -0.1700
Data Index: 6465148 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4350. Min Act: -0.1700
Data Index: 6896031 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.2475. Min Act: -0.1700
Data Index: 4128989 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4350. Min Act: -0.1700
Data Index: 6250915 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19