Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.4324. Min Act: -0.1700
Data Index: 4530708 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.4324. Min Act: -0.1700
Data Index: 3722514 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.3699. Min Act: -0.1700
Data Index: 6270874 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.3074. Min Act: -0.1700
Data Index: 8368896 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.3074. Min Act: -0.1700
Data Index: 4239295 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.2449. Min Act: -0.1700
Data Index: 60038 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1512. Min Act: -0.1700
Data Index: 6063862 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1824. Min Act: -0.1700
Data Index: 2710084 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1512. Min Act: -0.1700
Data Index: 7832211 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1512. Min Act: -0.1700
Data Index: 3282118 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1199. Min Act: -0.1700
Data Index: 8197176 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1199. Min Act: -0.1700
Data Index: 6676696 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.1199. Min Act: -0.1700
Data Index: 3356976 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0887. Min Act: -0.1700
Data Index: 8792130 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0887. Min Act: -0.1700
Data Index: 1810991 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0887. Min Act: -0.1700
Data Index: 2896205 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0887. Min Act: -0.1700
Data Index: 6911325 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0262. Min Act: -0.1700
Data Index: 3476552 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0574. Min Act: -0.1700
Data Index: 2157167 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4324. Min Range: -5.4324
Max Act: 5.0574. Min Act: -0.1700
Data Index: 6096297 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19