Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5200 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.3933. Min Act: -0.1700
Data Index: 2076036 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.2995. Min Act: -0.1700
Data Index: 633730 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.2058. Min Act: -0.1700
Data Index: 6618181 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.2370. Min Act: -0.1700
Data Index: 8741111 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.2370. Min Act: -0.1700
Data Index: 5830726 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.2058. Min Act: -0.1700
Data Index: 7175429 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.1745. Min Act: -0.1700
Data Index: 1997788 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.1433. Min Act: -0.1700
Data Index: 4555014 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.1433. Min Act: -0.1700
Data Index: 8364247 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.1433. Min Act: -0.1700
Data Index: 1594384 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.1120. Min Act: -0.1700
Data Index: 5843630 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.1120. Min Act: -0.1700
Data Index: 4172806 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.1120. Min Act: -0.1700
Data Index: 1631525 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.0183. Min Act: -0.1700
Data Index: 6405086 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.0183. Min Act: -0.1700
Data Index: 1914491 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3933. Min Range: -5.3933
Max Act: 5.0183. Min Act: -0.1700
Data Index: 8407348 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3933. Min Range: -5.3933
Max Act: 4.9870. Min Act: -0.1700
Data Index: 6889984 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3933. Min Range: -5.3933
Max Act: 4.9870. Min Act: -0.1700
Data Index: 2065485 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3933. Min Range: -5.3933
Max Act: 4.9870. Min Act: -0.1700
Data Index: 2247306 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3933. Min Range: -5.3933
Max Act: 4.9245. Min Act: -0.1700
Data Index: 2195081 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19