Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0980. Min Range: -7.0980
Max Act: 7.0980. Min Act: -0.1700
Data Index: 3251306 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0980. Min Range: -7.0980
Max Act: 7.0043. Min Act: -0.1700
Data Index: 1683244 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.9418. Min Act: -0.1700
Data Index: 8660991 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.9105. Min Act: -0.1700
Data Index: 7599911 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.8168. Min Act: -0.1700
Data Index: 6015912 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.7543. Min Act: -0.1700
Data Index: 2659932 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.7543. Min Act: -0.1700
Data Index: 7671821 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.7543. Min Act: -0.1700
Data Index: 5654749 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.6918. Min Act: -0.1700
Data Index: 4901614 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.7230. Min Act: -0.1700
Data Index: 4571760 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.7230. Min Act: -0.1700
Data Index: 5034557 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.7230. Min Act: -0.1700
Data Index: 4851628 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.6918. Min Act: -0.1700
Data Index: 3345301 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.6918. Min Act: -0.1700
Data Index: 3612241 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.6918. Min Act: -0.1700
Data Index: 1199992 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.6605. Min Act: -0.1700
Data Index: 5979150 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.6605. Min Act: -0.1700
Data Index: 3515012 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.6605. Min Act: -0.1700
Data Index: 8090301 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.6293. Min Act: -0.1700
Data Index: 8079907 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0980. Min Range: -7.0980
Max Act: 6.5980. Min Act: -0.1700
Data Index: 799102 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19