Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.9793. Min Act: -0.1700
Data Index: 2452714 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.9168. Min Act: -0.1700
Data Index: 7999791 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.8855. Min Act: -0.1700
Data Index: 7999792 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.8543. Min Act: -0.1700
Data Index: 2907053 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.8543. Min Act: -0.1700
Data Index: 167962 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.8230. Min Act: -0.1700
Data Index: 3044301 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.8230. Min Act: -0.1700
Data Index: 5922013 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.8230. Min Act: -0.1700
Data Index: 4238849 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.7918. Min Act: -0.1700
Data Index: 7084551 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.7918. Min Act: -0.1700
Data Index: 6391998 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.7605. Min Act: -0.1700
Data Index: 7113569 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.7293. Min Act: -0.1700
Data Index: 2934573 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.7293. Min Act: -0.1700
Data Index: 4331940 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.6980. Min Act: -0.1700
Data Index: 3046346 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.6668. Min Act: -0.1700
Data Index: 6656211 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.6668. Min Act: -0.1700
Data Index: 2447801 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.6668. Min Act: -0.1700
Data Index: 302123 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.6668. Min Act: -0.1700
Data Index: 7821957 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.6668. Min Act: -0.1700
Data Index: 5609284 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9793. Min Range: -4.9793
Max Act: 4.6668. Min Act: -0.1700
Data Index: 7960872 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19