Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3761 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6933. Min Range: -10.6933
Max Act: 10.6933. Min Act: -0.1700
Data Index: 8301697 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6933. Min Range: -10.6933
Max Act: 10.6933. Min Act: -0.1700
Data Index: 5215700 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6933. Min Range: -10.6933
Max Act: 10.5058. Min Act: -0.1700
Data Index: 6707951 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6933. Min Range: -10.6933
Max Act: 10.1933. Min Act: -0.1700
Data Index: 4923169 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6933. Min Range: -10.6933
Max Act: 10.1308. Min Act: -0.1700
Data Index: 1610823 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6933. Min Range: -10.6933
Max Act: 10.0683. Min Act: -0.1700
Data Index: 92937 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6933. Min Range: -10.6933
Max Act: 10.0058. Min Act: -0.1700
Data Index: 2245565 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6933. Min Range: -10.6933
Max Act: 10.0058. Min Act: -0.1700
Data Index: 5428571 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6933. Min Range: -10.6933
Max Act: 10.0683. Min Act: -0.1700
Data Index: 5486657 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.9433. Min Act: -0.1700
Data Index: 3941437 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.9433. Min Act: -0.1700
Data Index: 532079 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.9433. Min Act: -0.1700
Data Index: 1740604 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.8808. Min Act: -0.1690
Data Index: 3229646 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.8808. Min Act: -0.1700
Data Index: 6876023 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.8808. Min Act: -0.1700
Data Index: 6646241 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.8183. Min Act: -0.1700
Data Index: 520432 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.8183. Min Act: -0.1700
Data Index: 1107200 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.8183. Min Act: -0.1690
Data Index: 7908378 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.8183. Min Act: -0.1700
Data Index: 4855945 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6933. Min Range: -10.6933
Max Act: 9.8183. Min Act: -0.1700
Data Index: 4308210 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19