Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.6246. Min Act: -0.1700
Data Index: 4651684 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.6246. Min Act: -0.1700
Data Index: 65797 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.5621. Min Act: -0.1700
Data Index: 5509982 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.4371. Min Act: -0.1700
Data Index: 1939158 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.4371. Min Act: -0.1700
Data Index: 8777884 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.3746. Min Act: -0.1700
Data Index: 4493332 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.3121. Min Act: -0.1700
Data Index: 6356591 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.3746. Min Act: -0.1700
Data Index: 2467543 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.2496. Min Act: -0.1700
Data Index: 1255673 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.2496. Min Act: -0.1700
Data Index: 7356983 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.1871. Min Act: -0.1700
Data Index: 1104359 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.1871. Min Act: -0.1700
Data Index: 8791783 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.1246. Min Act: -0.1700
Data Index: 823503 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.0621. Min Act: -0.1700
Data Index: 3566982 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.0621. Min Act: -0.1700
Data Index: 5031495 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.1246. Min Act: -0.1700
Data Index: 6222359 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.1246. Min Act: -0.1700
Data Index: 1342657 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.1246. Min Act: -0.1700
Data Index: 7069021 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.0621. Min Act: -0.1700
Data Index: 6172553 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6246. Min Range: -9.6246
Max Act: 9.1246. Min Act: -0.1700
Data Index: 3958337 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19