Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.9680. Min Act: -0.1700
Data Index: 5723390 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.9680. Min Act: -0.1700
Data Index: 5779509 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.9367. Min Act: -0.1700
Data Index: 5460912 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.8742. Min Act: -0.1700
Data Index: 1157865 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.8742. Min Act: -0.1700
Data Index: 8671905 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.8742. Min Act: -0.1700
Data Index: 8784254 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.8429. Min Act: -0.1700
Data Index: 2514619 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.8429. Min Act: -0.1700
Data Index: 6871362 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.8117. Min Act: -0.1700
Data Index: 3268968 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.8117. Min Act: -0.1700
Data Index: 7559618 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.8117. Min Act: -0.1700
Data Index: 6927796 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.7960. Min Act: -0.1700
Data Index: 5860982 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.7648. Min Act: -0.1700
Data Index: 1599094 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.7804. Min Act: -0.1700
Data Index: 4758926 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.7804. Min Act: -0.1700
Data Index: 6130989 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.7960. Min Act: -0.1700
Data Index: 7080835 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.7491. Min Act: -0.1700
Data Index: 7209284 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.7648. Min Act: -0.1700
Data Index: 5107617 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.7491. Min Act: -0.1700
Data Index: 1647611 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9680. Min Range: -3.9680
Max Act: 3.7335. Min Act: -0.1700
Data Index: 2570357 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19