Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3189 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.9592. Min Act: -0.1700
Data Index: 2112840 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.8967. Min Act: -0.1700
Data Index: 3897925 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.8342. Min Act: -0.1700
Data Index: 1341128 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.8342. Min Act: -0.1700
Data Index: 3883932 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.8342. Min Act: -0.1700
Data Index: 4664938 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.8342. Min Act: -0.1700
Data Index: 8637641 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.8342. Min Act: -0.1700
Data Index: 468113 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.8029. Min Act: -0.1700
Data Index: 5376513 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.8029. Min Act: -0.1700
Data Index: 2771979 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.7873. Min Act: -0.1700
Data Index: 7935199 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.7873. Min Act: -0.1700
Data Index: 2962906 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.7716. Min Act: -0.1700
Data Index: 5067769 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.7403. Min Act: -0.1700
Data Index: 5353266 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.7403. Min Act: -0.1700
Data Index: 2221207 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.7403. Min Act: -0.1700
Data Index: 5295684 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.7247. Min Act: -0.1700
Data Index: 4486526 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.7091. Min Act: -0.1700
Data Index: 3047642 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.7091. Min Act: -0.1700
Data Index: 7772847 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.6934. Min Act: -0.1700
Data Index: 4034711 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9592. Min Range: -3.9592
Max Act: 3.6934. Min Act: -0.1700
Data Index: 3020057 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19