Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 995 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.4121. Min Act: -0.1700
Data Index: 7105980 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.3808. Min Act: -0.1700
Data Index: 7198896 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.2558. Min Act: -0.1700
Data Index: 3521917 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.2246. Min Act: -0.1700
Data Index: 484168 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.2246. Min Act: -0.1700
Data Index: 4110058 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.1933. Min Act: -0.1700
Data Index: 2244300 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.1621. Min Act: -0.1700
Data Index: 6166671 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.1308. Min Act: -0.1700
Data Index: 484169 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.0996. Min Act: -0.1700
Data Index: 7426620 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.0683. Min Act: -0.1700
Data Index: 2017612 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4121. Min Range: -5.4121
Max Act: 5.0058. Min Act: -0.1700
Data Index: 7477474 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4121. Min Range: -5.4121
Max Act: 4.9746. Min Act: -0.1700
Data Index: 2880499 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4121. Min Range: -5.4121
Max Act: 4.9746. Min Act: -0.1700
Data Index: 3238455 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4121. Min Range: -5.4121
Max Act: 4.9121. Min Act: -0.1700
Data Index: 4743227 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4121. Min Range: -5.4121
Max Act: 4.9121. Min Act: -0.1700
Data Index: 8829774 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4121. Min Range: -5.4121
Max Act: 4.9121. Min Act: -0.1700
Data Index: 8180893 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4121. Min Range: -5.4121
Max Act: 4.8496. Min Act: -0.1700
Data Index: 4110064 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4121. Min Range: -5.4121
Max Act: 4.8496. Min Act: -0.1700
Data Index: 7153667 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4121. Min Range: -5.4121
Max Act: 4.8808. Min Act: -0.1700
Data Index: 2567244 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4121. Min Range: -5.4121
Max Act: 4.8183. Min Act: -0.1700
Data Index: 5257252 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19