Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.9398. Min Act: -0.1700
Data Index: 944011 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.9085. Min Act: -0.1700
Data Index: 8810144 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.8773. Min Act: -0.1700
Data Index: 4982933 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.7835. Min Act: -0.1700
Data Index: 5230272 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.7835. Min Act: -0.1700
Data Index: 2472977 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.7523. Min Act: -0.1700
Data Index: 4985010 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.7523. Min Act: -0.1700
Data Index: 4037614 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.6273. Min Act: -0.1700
Data Index: 7162217 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.6273. Min Act: -0.1700
Data Index: 3020429 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.6273. Min Act: -0.1700
Data Index: 7627072 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.6273. Min Act: -0.1700
Data Index: 7389018 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.5335. Min Act: -0.1700
Data Index: 6290861 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.5335. Min Act: -0.1700
Data Index: 2553394 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.5335. Min Act: -0.1700
Data Index: 4110749 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.5023. Min Act: -0.1700
Data Index: 682487 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4710. Min Act: -0.1700
Data Index: 5534623 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4710. Min Act: -0.1700
Data Index: 1888863 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4710. Min Act: -0.1700
Data Index: 7393107 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4398. Min Act: -0.1700
Data Index: 969668 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9398. Min Range: -5.9398
Max Act: 5.4398. Min Act: -0.1700
Data Index: 3970108 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19