Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2257 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.4602. Min Act: -0.1700
Data Index: 6462335 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.3951. Min Act: -0.1699
Data Index: 5740898 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.3624. Min Act: -0.1695
Data Index: 1462618 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.3460. Min Act: -0.1700
Data Index: 5362772 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.3296. Min Act: -0.1700
Data Index: 6504569 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.2803. Min Act: -0.1700
Data Index: 3896858 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.2803. Min Act: -0.1700
Data Index: 5838921 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.2803. Min Act: -0.1699
Data Index: 2774181 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.2638. Min Act: -0.1700
Data Index: 79941 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.2473. Min Act: -0.1700
Data Index: 2489852 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.2142. Min Act: -0.1698
Data Index: 8525570 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.2142. Min Act: -0.1700
Data Index: 3750609 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.1976. Min Act: -0.1700
Data Index: 2231214 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.1810. Min Act: -0.1700
Data Index: 5740900 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.1976. Min Act: -0.1700
Data Index: 5547007 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.1810. Min Act: -0.1700
Data Index: 5838920 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.1810. Min Act: -0.1700
Data Index: 2578843 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.1643. Min Act: -0.1700
Data Index: 3343875 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.1643. Min Act: -0.1700
Data Index: 6132161 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4602. Min Range: -2.4602
Max Act: 2.1643. Min Act: -0.1700
Data Index: 2939833 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19