Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.6280. Min Act: -0.1700
Data Index: 6947472 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.3780. Min Act: -0.1700
Data Index: 5332967 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.3780. Min Act: -0.1700
Data Index: 2048311 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.3468. Min Act: -0.1700
Data Index: 8544301 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.3468. Min Act: -0.1700
Data Index: 8302130 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.3155. Min Act: -0.1700
Data Index: 7432692 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.2530. Min Act: -0.1700
Data Index: 908573 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.2530. Min Act: -0.1700
Data Index: 3881108 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.2218. Min Act: -0.1700
Data Index: 3087333 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.2218. Min Act: -0.1700
Data Index: 8407134 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.2218. Min Act: -0.1700
Data Index: 3284204 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.1905. Min Act: -0.1700
Data Index: 8788191 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.1593. Min Act: -0.1700
Data Index: 6002853 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.1593. Min Act: -0.1700
Data Index: 7308002 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.1280. Min Act: -0.1700
Data Index: 8443149 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.0968. Min Act: -0.1700
Data Index: 382338 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.0655. Min Act: -0.1700
Data Index: 7319209 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.0343. Min Act: -0.1700
Data Index: 6332580 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.0030. Min Act: -0.1700
Data Index: 2864169 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6280. Min Range: -5.6280
Max Act: 5.0030. Min Act: -0.1700
Data Index: 2507010 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19