Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.8471. Min Act: -0.1700
Data Index: 8196957 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.7533. Min Act: -0.1700
Data Index: 5216084 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.5346. Min Act: -0.1700
Data Index: 1973984 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.4721. Min Act: -0.1700
Data Index: 6318548 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.4096. Min Act: -0.1700
Data Index: 3896138 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.3783. Min Act: -0.1700
Data Index: 4130052 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.4096. Min Act: -0.1700
Data Index: 8261447 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.3783. Min Act: -0.1700
Data Index: 3973691 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.3783. Min Act: -0.1700
Data Index: 348589 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.3158. Min Act: -0.1700
Data Index: 5713548 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.2533. Min Act: -0.1700
Data Index: 3573245 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.2533. Min Act: -0.1700
Data Index: 2161515 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.2221. Min Act: -0.1700
Data Index: 7908750 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.2221. Min Act: -0.1700
Data Index: 7363380 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.1908. Min Act: -0.1700
Data Index: 7741665 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.1908. Min Act: -0.1700
Data Index: 4792609 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.1596. Min Act: -0.1700
Data Index: 5516319 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.1596. Min Act: -0.1700
Data Index: 5088499 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.1283. Min Act: -0.1700
Data Index: 3510052 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8471. Min Range: -6.8471
Max Act: 6.1283. Min Act: -0.1700
Data Index: 2073622 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19