Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 318 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.7398. Min Act: -0.1700
Data Index: 211995 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.4585. Min Act: -0.1700
Data Index: 2908661 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 2644809 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.1773. Min Act: -0.1700
Data Index: 5738838 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.1460. Min Act: -0.1700
Data Index: 5115618 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.1460. Min Act: -0.1700
Data Index: 6694011 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.1148. Min Act: -0.1700
Data Index: 4240592 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.0835. Min Act: -0.1700
Data Index: 3132392 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.0210. Min Act: -0.1700
Data Index: 4697148 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.0210. Min Act: -0.1700
Data Index: 89226 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7398. Min Range: -4.7398
Max Act: 4.0210. Min Act: -0.1700
Data Index: 2566521 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7398. Min Range: -4.7398
Max Act: 3.9897. Min Act: -0.1700
Data Index: 2489316 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7398. Min Range: -4.7398
Max Act: 3.9897. Min Act: -0.1700
Data Index: 7687017 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7398. Min Range: -4.7398
Max Act: 3.9585. Min Act: -0.1700
Data Index: 2889665 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7398. Min Range: -4.7398
Max Act: 3.9585. Min Act: -0.1700
Data Index: 7022349 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7398. Min Range: -4.7398
Max Act: 3.9585. Min Act: -0.1700
Data Index: 8087193 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7398. Min Range: -4.7398
Max Act: 3.9585. Min Act: -0.1700
Data Index: 5963714 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7398. Min Range: -4.7398
Max Act: 3.9272. Min Act: -0.1700
Data Index: 6878762 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7398. Min Range: -4.7398
Max Act: 3.9272. Min Act: -0.1700
Data Index: 78921 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7398. Min Range: -4.7398
Max Act: 3.9272. Min Act: -0.1700
Data Index: 7663879 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19