Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 239 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.9631. Min Act: -0.1700
Data Index: 5592652 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.7756. Min Act: -0.1700
Data Index: 4067148 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.7756. Min Act: -0.1700
Data Index: 7921045 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.7131. Min Act: -0.1700
Data Index: 1289213 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.7131. Min Act: -0.1700
Data Index: 7810610 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.6506. Min Act: -0.1700
Data Index: 4914689 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.6819. Min Act: -0.1700
Data Index: 8267306 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.6506. Min Act: -0.1700
Data Index: 8270890 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.6506. Min Act: -0.1700
Data Index: 1768069 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.5881. Min Act: -0.1700
Data Index: 7432933 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.5881. Min Act: -0.1700
Data Index: 4639595 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.5569. Min Act: -0.1700
Data Index: 5501585 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.5569. Min Act: -0.1700
Data Index: 6484767 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.4944. Min Act: -0.1700
Data Index: 8099773 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.4944. Min Act: -0.1700
Data Index: 7389192 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.4319. Min Act: -0.1700
Data Index: 3348281 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.4319. Min Act: -0.1700
Data Index: 2911916 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.4319. Min Act: -0.1700
Data Index: 6819367 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.4631. Min Act: -0.1700
Data Index: 1320042 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9631. Min Range: -6.9631
Max Act: 6.4006. Min Act: -0.1700
Data Index: 6436711 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19