Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2948 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.8167. Min Act: -0.1700
Data Index: 3191932 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.6292. Min Act: -0.1700
Data Index: 1893335 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.5354. Min Act: -0.1700
Data Index: 7857710 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.5042. Min Act: -0.1700
Data Index: 5320842 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.4729. Min Act: -0.1700
Data Index: 6772800 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.4417. Min Act: -0.1700
Data Index: 8456998 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.4104. Min Act: -0.1700
Data Index: 4804481 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.4104. Min Act: -0.1700
Data Index: 3314737 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.3792. Min Act: -0.1700
Data Index: 3384699 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.3479. Min Act: -0.1700
Data Index: 2370179 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.3792. Min Act: -0.1700
Data Index: 8562120 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.3792. Min Act: -0.1700
Data Index: 6915588 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.3167. Min Act: -0.1700
Data Index: 4486819 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.3167. Min Act: -0.1700
Data Index: 4734391 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.2854. Min Act: -0.1700
Data Index: 6689693 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.2854. Min Act: -0.1700
Data Index: 1913568 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.3167. Min Act: -0.1700
Data Index: 4821968 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.2854. Min Act: -0.1700
Data Index: 2383314 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.2854. Min Act: -0.1700
Data Index: 3660820 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8167. Min Range: -4.8167
Max Act: 4.2854. Min Act: -0.1700
Data Index: 7960936 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19