Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2319 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0410. Min Range: -5.0410
Max Act: 5.0410. Min Act: -0.1700
Data Index: 807414 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0410. Min Range: -5.0410
Max Act: 5.0410. Min Act: -0.1700
Data Index: 766290 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.9785. Min Act: -0.1700
Data Index: 5915860 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.9160. Min Act: -0.1700
Data Index: 4100232 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.8535. Min Act: -0.1700
Data Index: 122035 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.8222. Min Act: -0.1700
Data Index: 1998824 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.7910. Min Act: -0.1700
Data Index: 5006809 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.7910. Min Act: -0.1700
Data Index: 4436796 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.7597. Min Act: -0.1700
Data Index: 1435502 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.7597. Min Act: -0.1700
Data Index: 6272153 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.7285. Min Act: -0.1700
Data Index: 1485413 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.6972. Min Act: -0.1700
Data Index: 180079 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.6972. Min Act: -0.1700
Data Index: 4264691 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.6972. Min Act: -0.1700
Data Index: 3770673 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.6660. Min Act: -0.1700
Data Index: 8471628 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.6972. Min Act: -0.1700
Data Index: 7990727 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.6660. Min Act: -0.1700
Data Index: 2203559 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.6660. Min Act: -0.1700
Data Index: 7836420 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.6660. Min Act: -0.1700
Data Index: 5273322 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0410. Min Range: -5.0410
Max Act: 4.6347. Min Act: -0.1700
Data Index: 3412825 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19