Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2396 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.3985. Min Act: -0.1700
Data Index: 4376185 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.3360. Min Act: -0.1700
Data Index: 5849133 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.3360. Min Act: -0.1700
Data Index: 7291294 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.3360. Min Act: -0.1700
Data Index: 8528132 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.2735. Min Act: -0.1700
Data Index: 1413158 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.2735. Min Act: -0.1700
Data Index: 1766040 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.2110. Min Act: -0.1700
Data Index: 7163945 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.0860. Min Act: -0.1700
Data Index: 6587514 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.0860. Min Act: -0.1700
Data Index: 5892431 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.0235. Min Act: -0.1700
Data Index: 6055243 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.0235. Min Act: -0.1700
Data Index: 8493876 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.0235. Min Act: -0.1700
Data Index: 8193250 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.0860. Min Act: -0.1700
Data Index: 7984366 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.0235. Min Act: -0.1700
Data Index: 2581791 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3985. Min Range: -8.3985
Max Act: 7.9610. Min Act: -0.1700
Data Index: 4735166 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3985. Min Range: -8.3985
Max Act: 7.9610. Min Act: -0.1700
Data Index: 2523936 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3985. Min Range: -8.3985
Max Act: 8.0235. Min Act: -0.1700
Data Index: 6454601 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3985. Min Range: -8.3985
Max Act: 7.9610. Min Act: -0.1700
Data Index: 32953 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3985. Min Range: -8.3985
Max Act: 7.9610. Min Act: -0.1700
Data Index: 7382673 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3985. Min Range: -8.3985
Max Act: 7.9610. Min Act: -0.1700
Data Index: 5725995 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19