Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2315 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.6125. Min Act: -0.1700
Data Index: 2553707 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.6125. Min Act: -0.1700
Data Index: 8621712 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.6125. Min Act: -0.1700
Data Index: 576598 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.4562. Min Act: -0.1700
Data Index: 4335880 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.4250. Min Act: -0.1700
Data Index: 3198327 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.4250. Min Act: -0.1700
Data Index: 1436523 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.3625. Min Act: -0.1700
Data Index: 6397583 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.3312. Min Act: -0.1700
Data Index: 8094380 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.3312. Min Act: -0.1700
Data Index: 6507249 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.2687. Min Act: -0.1700
Data Index: 6551872 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.2687. Min Act: -0.1700
Data Index: 2461122 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.2375. Min Act: -0.1700
Data Index: 4929810 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.2375. Min Act: -0.1700
Data Index: 3369401 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.2062. Min Act: -0.1700
Data Index: 8231102 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.1750. Min Act: -0.1700
Data Index: 4229290 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.1750. Min Act: -0.1700
Data Index: 6346233 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.2062. Min Act: -0.1700
Data Index: 2569759 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.1750. Min Act: -0.1700
Data Index: 4279833 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.1750. Min Act: -0.1700
Data Index: 4069392 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6125. Min Range: -6.6125
Max Act: 6.1437. Min Act: -0.1700
Data Index: 7833704 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19