Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.9528. Min Act: -0.1700
Data Index: 6570752 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.5153. Min Act: -0.1700
Data Index: 2066363 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.4528. Min Act: -0.1700
Data Index: 1921577 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.4528. Min Act: -0.1700
Data Index: 1530651 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.3903. Min Act: -0.1700
Data Index: 2313077 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.4215. Min Act: -0.1700
Data Index: 1200335 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.3903. Min Act: -0.1700
Data Index: 6396148 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.4215. Min Act: -0.1700
Data Index: 8049230 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.3903. Min Act: -0.1700
Data Index: 3223011 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.3590. Min Act: -0.1700
Data Index: 4226551 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.3590. Min Act: -0.1700
Data Index: 5039523 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.2965. Min Act: -0.1700
Data Index: 2314476 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.2965. Min Act: -0.1700
Data Index: 5968645 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.2965. Min Act: -0.1700
Data Index: 548785 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.2965. Min Act: -0.1700
Data Index: 2805558 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.2653. Min Act: -0.1700
Data Index: 270162 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.2653. Min Act: -0.1700
Data Index: 6537324 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.2340. Min Act: -0.1700
Data Index: 2482112 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.2965. Min Act: -0.1700
Data Index: 7362454 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9528. Min Range: -5.9528
Max Act: 5.2653. Min Act: -0.1700
Data Index: 1432146 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19