Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.7456. Min Act: -0.1700
Data Index: 8524014 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.7144. Min Act: -0.1700
Data Index: 709705 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.6206. Min Act: -0.1700
Data Index: 709703 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.5894. Min Act: -0.1700
Data Index: 8524011 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.4956. Min Act: -0.1700
Data Index: 1896722 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.4644. Min Act: -0.1700
Data Index: 3164298 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.4956. Min Act: -0.1700
Data Index: 5792490 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.4644. Min Act: -0.1700
Data Index: 5453060 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.4331. Min Act: -0.1700
Data Index: 5334913 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.4019. Min Act: -0.1700
Data Index: 5453061 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.3706. Min Act: -0.1700
Data Index: 3087647 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.3706. Min Act: -0.1700
Data Index: 7465735 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.3394. Min Act: -0.1700
Data Index: 5081882 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.3394. Min Act: -0.1700
Data Index: 5882585 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.3081. Min Act: -0.1700
Data Index: 2809819 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.2769. Min Act: -0.1700
Data Index: 2927578 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.2769. Min Act: -0.1700
Data Index: 5792491 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.2456. Min Act: -0.1700
Data Index: 7492435 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.2456. Min Act: -0.1700
Data Index: 1405029 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7456. Min Range: -5.7456
Max Act: 5.2456. Min Act: -0.1700
Data Index: 6818284 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19