Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1912 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0053. Min Range: -5.0053
Max Act: 5.0053. Min Act: -0.1700
Data Index: 3506114 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.9740. Min Act: -0.1700
Data Index: 485023 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.8803. Min Act: -0.1700
Data Index: 104805 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.9115. Min Act: -0.1700
Data Index: 4855884 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.7240. Min Act: -0.1700
Data Index: 691767 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.7553. Min Act: -0.1700
Data Index: 7010978 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.6615. Min Act: -0.1700
Data Index: 1506419 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.6615. Min Act: -0.1700
Data Index: 2461677 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.6303. Min Act: -0.1700
Data Index: 4644123 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.6615. Min Act: -0.1700
Data Index: 1365417 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.6303. Min Act: -0.1700
Data Index: 7378946 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.5990. Min Act: -0.1700
Data Index: 2202864 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.5678. Min Act: -0.1700
Data Index: 3307449 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.5678. Min Act: -0.1700
Data Index: 6311120 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.5678. Min Act: -0.1700
Data Index: 5777516 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.5053. Min Act: -0.1700
Data Index: 7160883 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.5365. Min Act: -0.1700
Data Index: 4387711 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.5365. Min Act: -0.1700
Data Index: 389695 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.5365. Min Act: -0.1700
Data Index: 7280737 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0053. Min Range: -5.0053
Max Act: 4.5365. Min Act: -0.1700
Data Index: 8302868 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19