Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2330 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0786. Min Range: -5.0786
Max Act: 5.0786. Min Act: -0.1700
Data Index: 8637891 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0786. Min Range: -5.0786
Max Act: 5.0473. Min Act: -0.1700
Data Index: 2012266 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0786. Min Range: -5.0786
Max Act: 5.0161. Min Act: -0.1700
Data Index: 2922938 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0786. Min Range: -5.0786
Max Act: 5.0161. Min Act: -0.1700
Data Index: 2416497 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.9848. Min Act: -0.1700
Data Index: 6158511 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.9536. Min Act: -0.1700
Data Index: 8764420 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.9536. Min Act: -0.1700
Data Index: 647057 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.9223. Min Act: -0.1700
Data Index: 6158516 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.9223. Min Act: -0.1700
Data Index: 6158514 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.9223. Min Act: -0.1700
Data Index: 1983710 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.8911. Min Act: -0.1700
Data Index: 4533164 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.8911. Min Act: -0.1700
Data Index: 2787735 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.9223. Min Act: -0.1700
Data Index: 7028450 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.9223. Min Act: -0.1700
Data Index: 594580 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.9223. Min Act: -0.1700
Data Index: 6158512 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.8911. Min Act: -0.1700
Data Index: 6158515 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.8911. Min Act: -0.1700
Data Index: 6158517 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.8598. Min Act: -0.1700
Data Index: 5642121 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.8598. Min Act: -0.1700
Data Index: 8247703 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0786. Min Range: -5.0786
Max Act: 4.8286. Min Act: -0.1700
Data Index: 7787577 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19