Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.7795. Min Act: -0.1700
Data Index: 6349435 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.6545. Min Act: -0.1700
Data Index: 8293046 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.5607. Min Act: -0.1700
Data Index: 2925222 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4982. Min Act: -0.1700
Data Index: 5157393 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4670. Min Act: -0.1700
Data Index: 7452806 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4670. Min Act: -0.1700
Data Index: 8077561 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4357. Min Act: -0.1700
Data Index: 7061955 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4045. Min Act: -0.1700
Data Index: 8220820 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4045. Min Act: -0.1700
Data Index: 5733187 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.4045. Min Act: -0.1700
Data Index: 5246706 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3732. Min Act: -0.1700
Data Index: 130005 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3732. Min Act: -0.1700
Data Index: 4375567 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3420. Min Act: -0.1700
Data Index: 5258197 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3420. Min Act: -0.1700
Data Index: 4092731 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3420. Min Act: -0.1700
Data Index: 4492890 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3420. Min Act: -0.1700
Data Index: 665139 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3107. Min Act: -0.1700
Data Index: 1591717 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3107. Min Act: -0.1700
Data Index: 100906 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3107. Min Act: -0.1700
Data Index: 831673 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7795. Min Range: -4.7795
Max Act: 4.3107. Min Act: -0.1700
Data Index: 2514622 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19