Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3800 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3587. Min Range: -7.3587
Max Act: 7.3587. Min Act: -0.1700
Data Index: 1326211 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3587. Min Range: -7.3587
Max Act: 7.2337. Min Act: -0.1700
Data Index: 2617139 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3587. Min Range: -7.3587
Max Act: 7.2650. Min Act: -0.1700
Data Index: 1940738 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3587. Min Range: -7.3587
Max Act: 7.0775. Min Act: -0.1700
Data Index: 383882 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.9212. Min Act: -0.1700
Data Index: 3938869 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.9212. Min Act: -0.1700
Data Index: 665623 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.9212. Min Act: -0.1700
Data Index: 7727666 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.9212. Min Act: -0.1700
Data Index: 2010450 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.9212. Min Act: -0.1700
Data Index: 7519592 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.8900. Min Act: -0.1700
Data Index: 6788759 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.8587. Min Act: -0.1700
Data Index: 4008313 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.8587. Min Act: -0.1700
Data Index: 1895882 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.8275. Min Act: -0.1700
Data Index: 2202256 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.8275. Min Act: -0.1700
Data Index: 8085640 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.7337. Min Act: -0.1700
Data Index: 119933 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.7337. Min Act: -0.1700
Data Index: 7336456 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.7337. Min Act: -0.1700
Data Index: 6572600 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.7025. Min Act: -0.1700
Data Index: 7269339 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.6712. Min Act: -0.1700
Data Index: 4388060 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3587. Min Range: -7.3587
Max Act: 6.6712. Min Act: -0.1700
Data Index: 6828750 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19