Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1707. Min Range: -2.1707
Max Act: 2.1707. Min Act: -0.1700
Data Index: 1551744 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1707. Min Range: -2.1707
Max Act: 2.1707. Min Act: -0.1700
Data Index: 6824295 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1707. Min Range: -2.1707
Max Act: 2.0200. Min Act: -0.1700
Data Index: 3479488 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1707. Min Range: -2.1707
Max Act: 2.0200. Min Act: -0.1700
Data Index: 378056 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1707. Min Range: -2.1707
Max Act: 2.0200. Min Act: -0.1700
Data Index: 3479483 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1707. Min Range: -2.1707
Max Act: 2.0031. Min Act: -0.1700
Data Index: 7769116 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1707. Min Range: -2.1707
Max Act: 2.0200. Min Act: -0.1700
Data Index: 6824289 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9692. Min Act: -0.1700
Data Index: 7527019 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9692. Min Act: -0.1700
Data Index: 3479486 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9692. Min Act: -0.1700
Data Index: 3479487 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9692. Min Act: -0.1700
Data Index: 765654 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9692. Min Act: -0.1700
Data Index: 2056730 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9523. Min Act: -0.1699
Data Index: 2056732 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9353. Min Act: -0.1698
Data Index: 4895045 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9523. Min Act: -0.1700
Data Index: 1335200 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9353. Min Act: -0.1700
Data Index: 8289076 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9523. Min Act: -0.1700
Data Index: 7505981 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9353. Min Act: -0.1700
Data Index: 6824302 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9523. Min Act: -0.1700
Data Index: 7552622 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1707. Min Range: -2.1707
Max Act: 1.9523. Min Act: -0.1700
Data Index: 7252147 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19