Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6223 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0632. Min Range: -5.0632
Max Act: 5.0632. Min Act: -0.1700
Data Index: 3842416 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0632. Min Range: -5.0632
Max Act: 5.0632. Min Act: -0.1700
Data Index: 3200036 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0632. Min Range: -5.0632
Max Act: 5.0320. Min Act: -0.1700
Data Index: 6754524 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.9382. Min Act: -0.1700
Data Index: 6175316 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.9695. Min Act: -0.1700
Data Index: 1655976 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.9695. Min Act: -0.1700
Data Index: 7209110 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.9382. Min Act: -0.1700
Data Index: 7209112 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.9382. Min Act: -0.1700
Data Index: 6666272 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.9070. Min Act: -0.1700
Data Index: 4727516 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.9070. Min Act: -0.1700
Data Index: 829628 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8757. Min Act: -0.1700
Data Index: 6666970 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8757. Min Act: -0.1700
Data Index: 5652130 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8757. Min Act: -0.1700
Data Index: 8734049 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8757. Min Act: -0.1700
Data Index: 5012744 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8445. Min Act: -0.1700
Data Index: 5682209 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8445. Min Act: -0.1700
Data Index: 2571559 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8132. Min Act: -0.1700
Data Index: 5109670 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8132. Min Act: -0.1700
Data Index: 3618632 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8132. Min Act: -0.1700
Data Index: 4822037 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0632. Min Range: -5.0632
Max Act: 4.8132. Min Act: -0.1700
Data Index: 31296 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19