Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4454 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.4644. Min Act: -0.1700
Data Index: 2869526 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.4332. Min Act: -0.1700
Data Index: 3015478 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.3394. Min Act: -0.1700
Data Index: 3673373 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.1832. Min Act: -0.1700
Data Index: 4800235 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.1519. Min Act: -0.1700
Data Index: 5408187 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.1519. Min Act: -0.1700
Data Index: 1259515 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.0894. Min Act: -0.1700
Data Index: 6164712 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.1207. Min Act: -0.1700
Data Index: 4986413 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.0894. Min Act: -0.1700
Data Index: 2039919 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.1207. Min Act: -0.1700
Data Index: 907601 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.0269. Min Act: -0.1700
Data Index: 2233894 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4644. Min Range: -5.4644
Max Act: 5.0269. Min Act: -0.1700
Data Index: 2823031 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4644. Min Range: -5.4644
Max Act: 4.9957. Min Act: -0.1700
Data Index: 1459509 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4644. Min Range: -5.4644
Max Act: 4.9957. Min Act: -0.1700
Data Index: 7115378 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4644. Min Range: -5.4644
Max Act: 4.9644. Min Act: -0.1700
Data Index: 2159801 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4644. Min Range: -5.4644
Max Act: 4.9644. Min Act: -0.1700
Data Index: 5508592 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4644. Min Range: -5.4644
Max Act: 4.9332. Min Act: -0.1700
Data Index: 6982526 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4644. Min Range: -5.4644
Max Act: 4.9332. Min Act: -0.1700
Data Index: 5923646 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4644. Min Range: -5.4644
Max Act: 4.9644. Min Act: -0.1700
Data Index: 4960403 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4644. Min Range: -5.4644
Max Act: 4.9019. Min Act: -0.1700
Data Index: 2323356 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19