Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.3483. Min Act: -0.1700
Data Index: 4559144 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.1920. Min Act: -0.1700
Data Index: 3135412 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.1920. Min Act: -0.1700
Data Index: 3538269 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.1295. Min Act: -0.1700
Data Index: 7884896 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.1607. Min Act: -0.1700
Data Index: 4935449 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.1295. Min Act: -0.1700
Data Index: 5761037 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.1295. Min Act: -0.1700
Data Index: 3815635 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.1295. Min Act: -0.1700
Data Index: 476511 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0982. Min Act: -0.1700
Data Index: 6382661 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.1295. Min Act: -0.1700
Data Index: 8418781 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0982. Min Act: -0.1700
Data Index: 7065429 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0982. Min Act: -0.1700
Data Index: 2396624 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0982. Min Act: -0.1700
Data Index: 1733150 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0670. Min Act: -0.1700
Data Index: 8648995 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0670. Min Act: -0.1700
Data Index: 2592037 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0670. Min Act: -0.1700
Data Index: 8466124 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0357. Min Act: -0.1700
Data Index: 2790946 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0357. Min Act: -0.1700
Data Index: 6640541 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0670. Min Act: -0.1700
Data Index: 6423781 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3483. Min Range: -4.3483
Max Act: 4.0670. Min Act: -0.1700
Data Index: 910313 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19