Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4237 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.5887. Min Act: -0.1700
Data Index: 2960276 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.5887. Min Act: -0.1700
Data Index: 7826380 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.5887. Min Act: -0.1700
Data Index: 4679583 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.5726. Min Act: -0.1700
Data Index: 8285872 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.5080. Min Act: -0.1700
Data Index: 7225669 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4918. Min Act: -0.1700
Data Index: 3085461 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4756. Min Act: -0.1700
Data Index: 4238303 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4918. Min Act: -0.1700
Data Index: 1847238 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4918. Min Act: -0.1700
Data Index: 5008858 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4756. Min Act: -0.1700
Data Index: 5380794 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4593. Min Act: -0.1700
Data Index: 7568866 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4593. Min Act: -0.1700
Data Index: 694429 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4756. Min Act: -0.1700
Data Index: 7626332 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4431. Min Act: -0.1700
Data Index: 660359 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4268. Min Act: -0.1700
Data Index: 1613466 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4268. Min Act: -0.1700
Data Index: 2705701 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4268. Min Act: -0.1700
Data Index: 7916302 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4268. Min Act: -0.1700
Data Index: 671216 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4105. Min Act: -0.1700
Data Index: 5669001 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5887. Min Range: -2.5887
Max Act: 2.4105. Min Act: -0.1700
Data Index: 719468 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19