Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 679 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.5272. Min Act: -0.1700
Data Index: 4565887 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.5272. Min Act: -0.1700
Data Index: 1234054 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.5110. Min Act: -0.1700
Data Index: 4950330 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.4948. Min Act: -0.1700
Data Index: 6747403 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.4624. Min Act: -0.1700
Data Index: 141444 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.4461. Min Act: -0.1700
Data Index: 3116669 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.4461. Min Act: -0.1700
Data Index: 6307080 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.4786. Min Act: -0.1700
Data Index: 4397339 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.4786. Min Act: -0.1700
Data Index: 7227553 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.3972. Min Act: -0.1700
Data Index: 173662 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.3809. Min Act: -0.1700
Data Index: 8024004 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.4135. Min Act: -0.1700
Data Index: 2636 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.4135. Min Act: -0.1700
Data Index: 3543811 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.3972. Min Act: -0.1700
Data Index: 631217 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.3645. Min Act: -0.1700
Data Index: 5386453 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.3972. Min Act: -0.1700
Data Index: 4294643 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.3809. Min Act: -0.1700
Data Index: 4401249 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.3482. Min Act: -0.1700
Data Index: 8011714 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.3809. Min Act: -0.1700
Data Index: 341775 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5272. Min Range: -2.5272
Max Act: 2.4135. Min Act: -0.1700
Data Index: 425386 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19