Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4003 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.3586. Min Act: -0.1700
Data Index: 4424377 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.3273. Min Act: -0.1700
Data Index: 4943165 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.2336. Min Act: -0.1700
Data Index: 3237003 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.1711. Min Act: -0.1700
Data Index: 6088392 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.1086. Min Act: -0.1700
Data Index: 4463408 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.1086. Min Act: -0.1700
Data Index: 4534990 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0773. Min Act: -0.1700
Data Index: 713422 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.1086. Min Act: -0.1700
Data Index: 1513846 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0773. Min Act: -0.1700
Data Index: 5787574 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0773. Min Act: -0.1700
Data Index: 6236147 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0461. Min Act: -0.1700
Data Index: 720895 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0461. Min Act: -0.1700
Data Index: 6203646 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0773. Min Act: -0.1700
Data Index: 4531451 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0461. Min Act: -0.1700
Data Index: 5037729 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0148. Min Act: -0.1700
Data Index: 648688 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0148. Min Act: -0.1700
Data Index: 406855 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0461. Min Act: -0.1700
Data Index: 2214244 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3586. Min Range: -5.3586
Max Act: 4.9836. Min Act: -0.1700
Data Index: 3102547 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0148. Min Act: -0.1700
Data Index: 4054301 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3586. Min Range: -5.3586
Max Act: 5.0148. Min Act: -0.1700
Data Index: 2514301 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19