Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1116 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.3425. Min Act: -0.1700
Data Index: 7690286 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.2800. Min Act: -0.1700
Data Index: 1081655 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.2800. Min Act: -0.1700
Data Index: 6978100 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.2175. Min Act: -0.1700
Data Index: 7102738 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.2487. Min Act: -0.1700
Data Index: 1896414 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.1550. Min Act: -0.1700
Data Index: 8747501 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.0612. Min Act: -0.1700
Data Index: 8377165 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.0612. Min Act: -0.1700
Data Index: 1609587 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.0300. Min Act: -0.1700
Data Index: 7032805 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3425. Min Range: -7.3425
Max Act: 7.0300. Min Act: -0.1700
Data Index: 7247368 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9987. Min Act: -0.1700
Data Index: 3675852 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9987. Min Act: -0.1700
Data Index: 3571396 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9675. Min Act: -0.1700
Data Index: 5181640 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9362. Min Act: -0.1700
Data Index: 5910697 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9362. Min Act: -0.1700
Data Index: 7720677 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9675. Min Act: -0.1700
Data Index: 538381 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9362. Min Act: -0.1700
Data Index: 905318 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9362. Min Act: -0.1700
Data Index: 3290310 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9362. Min Act: -0.1700
Data Index: 604978 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3425. Min Range: -7.3425
Max Act: 6.9050. Min Act: -0.1700
Data Index: 4205442 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19