Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.5614. Min Act: -0.1700
Data Index: 6008884 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.2489. Min Act: -0.1700
Data Index: 8735392 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 7826165 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 2725400 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5614. Min Range: -6.5614
Max Act: 6.0302. Min Act: -0.1700
Data Index: 6773821 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9989. Min Act: -0.1700
Data Index: 1669274 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9052. Min Act: -0.1700
Data Index: 5707902 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9052. Min Act: -0.1700
Data Index: 8415148 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9364. Min Act: -0.1700
Data Index: 6165235 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9364. Min Act: -0.1700
Data Index: 2947586 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9364. Min Act: -0.1700
Data Index: 689595 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9052. Min Act: -0.1700
Data Index: 1515453 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9052. Min Act: -0.1700
Data Index: 1053500 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9052. Min Act: -0.1700
Data Index: 7848196 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.9364. Min Act: -0.1700
Data Index: 38941 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.8427. Min Act: -0.1700
Data Index: 4508210 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.8739. Min Act: -0.1700
Data Index: 1508528 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.8739. Min Act: -0.1700
Data Index: 2295229 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.8427. Min Act: -0.1700
Data Index: 869777 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5614. Min Range: -6.5614
Max Act: 5.8114. Min Act: -0.1700
Data Index: 5392887 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19