Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.3833. Min Act: -0.1700
Data Index: 6339448 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.2270. Min Act: -0.1700
Data Index: 7976351 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.1958. Min Act: -0.1700
Data Index: 5260812 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.1645. Min Act: -0.1700
Data Index: 4375061 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.1020. Min Act: -0.1700
Data Index: 7395664 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.0395. Min Act: -0.1700
Data Index: 4946911 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.0083. Min Act: -0.1700
Data Index: 4595321 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.0083. Min Act: -0.1700
Data Index: 8271344 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.0083. Min Act: -0.1700
Data Index: 4312197 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.0083. Min Act: -0.1700
Data Index: 4142346 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3833. Min Range: -6.3833
Max Act: 6.0083. Min Act: -0.1700
Data Index: 7754899 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3833. Min Range: -6.3833
Max Act: 5.9145. Min Act: -0.1700
Data Index: 6977582 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3833. Min Range: -6.3833
Max Act: 5.9770. Min Act: -0.1700
Data Index: 3708058 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3833. Min Range: -6.3833
Max Act: 5.9458. Min Act: -0.1700
Data Index: 2462380 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3833. Min Range: -6.3833
Max Act: 5.9145. Min Act: -0.1700
Data Index: 7692309 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3833. Min Range: -6.3833
Max Act: 5.9145. Min Act: -0.1700
Data Index: 8659393 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3833. Min Range: -6.3833
Max Act: 5.8520. Min Act: -0.1700
Data Index: 3198902 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3833. Min Range: -6.3833
Max Act: 5.7895. Min Act: -0.1700
Data Index: 5894827 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3833. Min Range: -6.3833
Max Act: 5.8208. Min Act: -0.1700
Data Index: 2652500 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3833. Min Range: -6.3833
Max Act: 5.8208. Min Act: -0.1700
Data Index: 7715997 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19