Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.2893. Min Act: -0.1700
Data Index: 5276035 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.2579. Min Act: -0.1700
Data Index: 8196571 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.2579. Min Act: -0.1700
Data Index: 3251029 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.2264. Min Act: -0.1700
Data Index: 8250815 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.1793. Min Act: -0.1700
Data Index: 8744317 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.1635. Min Act: -0.1700
Data Index: 2674894 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.1793. Min Act: -0.1700
Data Index: 327729 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.1635. Min Act: -0.1700
Data Index: 785437 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.1321. Min Act: -0.1700
Data Index: 4135634 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.1321. Min Act: -0.1700
Data Index: 3976118 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0848. Min Act: -0.1700
Data Index: 2201704 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0690. Min Act: -0.1700
Data Index: 1061932 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0848. Min Act: -0.1700
Data Index: 6036474 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0532. Min Act: -0.1700
Data Index: 3563363 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0690. Min Act: -0.1700
Data Index: 7029873 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0375. Min Act: -0.1700
Data Index: 8567817 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0532. Min Act: -0.1700
Data Index: 7809843 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0375. Min Act: -0.1700
Data Index: 8502120 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0217. Min Act: -0.1700
Data Index: 5851085 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2893. Min Range: -3.2893
Max Act: 3.0059. Min Act: -0.1700
Data Index: 5507777 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19