Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.9515. Min Act: -0.1700
Data Index: 7840184 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.9202. Min Act: -0.1700
Data Index: 2392906 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8890. Min Act: -0.1700
Data Index: 1827106 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8264. Min Act: -0.1700
Data Index: 7658798 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8264. Min Act: -0.1700
Data Index: 3431242 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8577. Min Act: -0.1700
Data Index: 8625825 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8264. Min Act: -0.1700
Data Index: 93752 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8264. Min Act: -0.1700
Data Index: 6785007 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8264. Min Act: -0.1700
Data Index: 5075434 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8264. Min Act: -0.1700
Data Index: 3629679 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8264. Min Act: -0.1700
Data Index: 5974130 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8108. Min Act: -0.1700
Data Index: 2309307 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8108. Min Act: -0.1700
Data Index: 5958264 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8264. Min Act: -0.1700
Data Index: 3940414 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.7952. Min Act: -0.1700
Data Index: 649909 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.8108. Min Act: -0.1700
Data Index: 1976644 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.7952. Min Act: -0.1700
Data Index: 21001 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.7952. Min Act: -0.1700
Data Index: 7827424 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.7952. Min Act: -0.1700
Data Index: 7543479 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9515. Min Range: -3.9515
Max Act: 3.7795. Min Act: -0.1700
Data Index: 1988719 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19