Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.5989. Min Act: -0.1700
Data Index: 2143514 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.5051. Min Act: -0.1700
Data Index: 1995011 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.3489. Min Act: -0.1700
Data Index: 8467666 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.3489. Min Act: -0.1700
Data Index: 1888942 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.3176. Min Act: -0.1700
Data Index: 7675703 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.2864. Min Act: -0.1700
Data Index: 90630 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.2864. Min Act: -0.1700
Data Index: 8058741 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.2551. Min Act: -0.1700
Data Index: 3964301 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.2239. Min Act: -0.1700
Data Index: 303392 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.1926. Min Act: -0.1700
Data Index: 7786971 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.1926. Min Act: -0.1700
Data Index: 6395047 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.1926. Min Act: -0.1700
Data Index: 1892782 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.0989. Min Act: -0.1700
Data Index: 5727406 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.1301. Min Act: -0.1700
Data Index: 4437546 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.1301. Min Act: -0.1700
Data Index: 2681474 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.0989. Min Act: -0.1700
Data Index: 4370961 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.0989. Min Act: -0.1700
Data Index: 8076709 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.0989. Min Act: -0.1700
Data Index: 1824651 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.0989. Min Act: -0.1700
Data Index: 2247932 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5989. Min Range: -6.5989
Max Act: 6.0989. Min Act: -0.1700
Data Index: 6579544 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19