Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.5845. Min Act: -0.1700
Data Index: 7413623 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.4907. Min Act: -0.1700
Data Index: 5057445 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.4907. Min Act: -0.1700
Data Index: 772036 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.4282. Min Act: -0.1700
Data Index: 1137324 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.3970. Min Act: -0.1700
Data Index: 1137326 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.3970. Min Act: -0.1700
Data Index: 8538049 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.3032. Min Act: -0.1700
Data Index: 7637858 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.2095. Min Act: -0.1700
Data Index: 8318450 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.2407. Min Act: -0.1700
Data Index: 6210284 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.2407. Min Act: -0.1700
Data Index: 3507562 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.1782. Min Act: -0.1700
Data Index: 1587816 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.1782. Min Act: -0.1700
Data Index: 7397990 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.1470. Min Act: -0.1700
Data Index: 509809 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.1157. Min Act: -0.1700
Data Index: 1117302 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.0220. Min Act: -0.1700
Data Index: 3591126 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.0220. Min Act: -0.1700
Data Index: 950146 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.0532. Min Act: -0.1700
Data Index: 5573566 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.0220. Min Act: -0.1700
Data Index: 6834917 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.0532. Min Act: -0.1700
Data Index: 3629730 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5845. Min Range: -6.5845
Max Act: 6.0532. Min Act: -0.1700
Data Index: 2143485 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19