Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2536 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.4357. Min Act: -0.1700
Data Index: 6967790 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.3103. Min Act: -0.1700
Data Index: 7596223 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.2317. Min Act: -0.1700
Data Index: 190940 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.1374. Min Act: -0.1700
Data Index: 7076837 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.1058. Min Act: -0.1700
Data Index: 7887489 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.1216. Min Act: -0.1700
Data Index: 8650508 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.1216. Min Act: -0.1700
Data Index: 1563014 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.1058. Min Act: -0.1700
Data Index: 7259692 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.1216. Min Act: -0.1700
Data Index: 8499726 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.1058. Min Act: -0.1700
Data Index: 7397341 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.1058. Min Act: -0.1700
Data Index: 5109656 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.0901. Min Act: -0.1700
Data Index: 3835415 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.0901. Min Act: -0.1700
Data Index: 5556641 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.0743. Min Act: -0.1700
Data Index: 3118569 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.0743. Min Act: -0.1700
Data Index: 7818471 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.0428. Min Act: -0.1700
Data Index: 4556368 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.0901. Min Act: -0.1700
Data Index: 6459802 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.0585. Min Act: -0.1700
Data Index: 6193077 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.0585. Min Act: -0.1700
Data Index: 5442275 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4357. Min Range: -3.4357
Max Act: 3.0743. Min Act: -0.1700
Data Index: 359052 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19