Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2601 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.6504. Min Act: -0.1700
Data Index: 4258472 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.5254. Min Act: -0.1700
Data Index: 6937616 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.4629. Min Act: -0.1700
Data Index: 8742051 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.4004. Min Act: -0.1700
Data Index: 165108 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.4629. Min Act: -0.1700
Data Index: 6239006 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.4004. Min Act: -0.1700
Data Index: 8259112 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.2754. Min Act: -0.1700
Data Index: 2862292 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.2129. Min Act: -0.1700
Data Index: 742647 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.2129. Min Act: -0.1700
Data Index: 8106368 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.2129. Min Act: -0.1700
Data Index: 4186176 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.2129. Min Act: -0.1700
Data Index: 7687260 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.2129. Min Act: -0.1700
Data Index: 5962437 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1817. Min Act: -0.1700
Data Index: 956674 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1817. Min Act: -0.1700
Data Index: 6450417 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1817. Min Act: -0.1700
Data Index: 8600461 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1817. Min Act: -0.1700
Data Index: 6165255 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1817. Min Act: -0.1700
Data Index: 3729542 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1504. Min Act: -0.1700
Data Index: 3383394 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1192. Min Act: -0.1700
Data Index: 4237889 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6504. Min Range: -5.6504
Max Act: 5.1504. Min Act: -0.1700
Data Index: 6899887 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19