Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4298 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1820. Min Range: -9.1820
Max Act: 9.1820. Min Act: -0.1700
Data Index: 6276046 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.8070. Min Act: -0.1700
Data Index: 6517490 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.6195. Min Act: -0.1700
Data Index: 6368403 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.6195. Min Act: -0.1700
Data Index: 2060166 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.4945. Min Act: -0.1700
Data Index: 5445805 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.4945. Min Act: -0.1700
Data Index: 3963320 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.5570. Min Act: -0.1700
Data Index: 2161099 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.4945. Min Act: -0.1700
Data Index: 7318050 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.4320. Min Act: -0.1700
Data Index: 8572586 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.4320. Min Act: -0.1700
Data Index: 4759065 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.4320. Min Act: -0.1700
Data Index: 1113301 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.4320. Min Act: -0.1700
Data Index: 4786382 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.4320. Min Act: -0.1700
Data Index: 7854719 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.3695. Min Act: -0.1700
Data Index: 2981624 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.3695. Min Act: -0.1700
Data Index: 3952697 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.4320. Min Act: -0.1700
Data Index: 3879519 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.3695. Min Act: -0.1700
Data Index: 8414195 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.3695. Min Act: -0.1700
Data Index: 8274879 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.3070. Min Act: -0.1700
Data Index: 7271882 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1820. Min Range: -9.1820
Max Act: 8.3070. Min Act: -0.1700
Data Index: 6630399 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19