Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2025. Min Range: -5.2025
Max Act: 5.2025. Min Act: -0.1700
Data Index: 8373179 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2025. Min Range: -5.2025
Max Act: 5.0775. Min Act: -0.1700
Data Index: 5034489 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2025. Min Range: -5.2025
Max Act: 5.0462. Min Act: -0.1700
Data Index: 6075080 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2025. Min Range: -5.2025
Max Act: 5.0462. Min Act: -0.1700
Data Index: 6860714 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2025. Min Range: -5.2025
Max Act: 5.0150. Min Act: -0.1700
Data Index: 3006714 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2025. Min Range: -5.2025
Max Act: 5.0150. Min Act: -0.1700
Data Index: 8642874 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.9525. Min Act: -0.1700
Data Index: 8661408 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.9525. Min Act: -0.1700
Data Index: 8326921 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.9212. Min Act: -0.1700
Data Index: 601811 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8900. Min Act: -0.1700
Data Index: 310737 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8900. Min Act: -0.1700
Data Index: 2825662 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8587. Min Act: -0.1700
Data Index: 5398320 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8587. Min Act: -0.1700
Data Index: 6700590 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8275. Min Act: -0.1700
Data Index: 670630 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8275. Min Act: -0.1700
Data Index: 5069044 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.7962. Min Act: -0.1700
Data Index: 3082813 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8275. Min Act: -0.1700
Data Index: 4825305 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8587. Min Act: -0.1700
Data Index: 3193600 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8275. Min Act: -0.1700
Data Index: 1634939 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2025. Min Range: -5.2025
Max Act: 4.8275. Min Act: -0.1700
Data Index: 4138466 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19