Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4426 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3575. Min Range: -6.3575
Max Act: 6.3575. Min Act: -0.1700
Data Index: 6754346 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3575. Min Range: -6.3575
Max Act: 6.2950. Min Act: -0.1700
Data Index: 1619913 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3575. Min Range: -6.3575
Max Act: 6.2325. Min Act: -0.1700
Data Index: 3887600 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3575. Min Range: -6.3575
Max Act: 6.0763. Min Act: -0.1700
Data Index: 3271548 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3575. Min Range: -6.3575
Max Act: 6.0450. Min Act: -0.1700
Data Index: 5637434 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3575. Min Range: -6.3575
Max Act: 6.0450. Min Act: -0.1700
Data Index: 6835587 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3575. Min Range: -6.3575
Max Act: 6.0763. Min Act: -0.1700
Data Index: 2983285 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3575. Min Range: -6.3575
Max Act: 6.0138. Min Act: -0.1700
Data Index: 973256 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.9825. Min Act: -0.1700
Data Index: 162936 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.9513. Min Act: -0.1700
Data Index: 7138728 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.9513. Min Act: -0.1700
Data Index: 1633782 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.9513. Min Act: -0.1700
Data Index: 393972 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.9200. Min Act: -0.1700
Data Index: 8342809 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.8575. Min Act: -0.1700
Data Index: 8579067 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.8888. Min Act: -0.1700
Data Index: 6094843 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.8888. Min Act: -0.1700
Data Index: 6101312 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.8888. Min Act: -0.1700
Data Index: 6128042 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.8575. Min Act: -0.1700
Data Index: 4863033 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.8575. Min Act: -0.1700
Data Index: 448899 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3575. Min Range: -6.3575
Max Act: 5.8575. Min Act: -0.1700
Data Index: 284228 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19