Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4228 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.8502. Min Act: -0.1700
Data Index: 7228210 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.8502. Min Act: -0.1700
Data Index: 7517062 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.8502. Min Act: -0.1700
Data Index: 3228036 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.7564. Min Act: -0.1700
Data Index: 1886887 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.7251. Min Act: -0.1700
Data Index: 6363177 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.7251. Min Act: -0.1700
Data Index: 4239374 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 6142055 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6938. Min Act: -0.1700
Data Index: 7789472 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 1407124 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 7750579 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 3562364 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 7375741 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 8155556 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 6020605 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 5303365 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 294425 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 5171743 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6312. Min Act: -0.1700
Data Index: 1026518 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.6625. Min Act: -0.1700
Data Index: 3220168 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8502. Min Range: -3.8502
Max Act: 3.5686. Min Act: -0.1700
Data Index: 4904789 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19