Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4009 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.3684. Min Act: -0.1700
Data Index: 4221705 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.1957. Min Act: -0.1700
Data Index: 6344094 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.2114. Min Act: -0.1700
Data Index: 2330035 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.1957. Min Act: -0.1700
Data Index: 2951718 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.1485. Min Act: -0.1700
Data Index: 2395287 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.1327. Min Act: -0.1700
Data Index: 2288810 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.1327. Min Act: -0.1700
Data Index: 5673164 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.1170. Min Act: -0.1700
Data Index: 1275139 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0539. Min Act: -0.1700
Data Index: 8529786 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0697. Min Act: -0.1700
Data Index: 1275148 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0539. Min Act: -0.1700
Data Index: 2797479 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0381. Min Act: -0.1700
Data Index: 4945536 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0223. Min Act: -0.1700
Data Index: 3428167 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0065. Min Act: -0.1700
Data Index: 2453087 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0065. Min Act: -0.1700
Data Index: 8214322 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0065. Min Act: -0.1700
Data Index: 1275120 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0065. Min Act: -0.1700
Data Index: 7243357 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3684. Min Range: -3.3684
Max Act: 3.0065. Min Act: -0.1700
Data Index: 6527948 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3684. Min Range: -3.3684
Max Act: 2.9907. Min Act: -0.1700
Data Index: 2667809 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3684. Min Range: -3.3684
Max Act: 2.9907. Min Act: -0.1700
Data Index: 6683329 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19