Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.7284. Min Act: -0.1700
Data Index: 6810293 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.6971. Min Act: -0.1700
Data Index: 1855984 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.6659. Min Act: -0.1700
Data Index: 6380768 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.6659. Min Act: -0.1700
Data Index: 8633580 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.6346. Min Act: -0.1700
Data Index: 4594580 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5721. Min Act: -0.1700
Data Index: 1122290 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.6034. Min Act: -0.1700
Data Index: 2483608 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5409. Min Act: -0.1700
Data Index: 5819896 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5721. Min Act: -0.1700
Data Index: 6129114 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5721. Min Act: -0.1700
Data Index: 7590741 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.6034. Min Act: -0.1700
Data Index: 7820075 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5721. Min Act: -0.1700
Data Index: 8511320 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5409. Min Act: -0.1700
Data Index: 1968079 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5409. Min Act: -0.1700
Data Index: 1682597 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5409. Min Act: -0.1700
Data Index: 5437577 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5096. Min Act: -0.1700
Data Index: 1594558 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5409. Min Act: -0.1700
Data Index: 3006312 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5096. Min Act: -0.1700
Data Index: 3100982 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5096. Min Act: -0.1700
Data Index: 3121499 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7284. Min Range: -4.7284
Max Act: 4.5096. Min Act: -0.1700
Data Index: 4768485 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19