Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2549 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.9657. Min Act: -0.1700
Data Index: 7735706 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.8720. Min Act: -0.1700
Data Index: 2331038 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.8407. Min Act: -0.1700
Data Index: 1942598 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.8407. Min Act: -0.1700
Data Index: 3768987 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.8407. Min Act: -0.1700
Data Index: 6657561 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.8407. Min Act: -0.1700
Data Index: 6137695 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.8407. Min Act: -0.1700
Data Index: 693624 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.8095. Min Act: -0.1700
Data Index: 3365524 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.8095. Min Act: -0.1700
Data Index: 5163978 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.7782. Min Act: -0.1700
Data Index: 5646905 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.7782. Min Act: -0.1700
Data Index: 5104114 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.7470. Min Act: -0.1700
Data Index: 6248020 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.7470. Min Act: -0.1700
Data Index: 7522231 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.7157. Min Act: -0.1700
Data Index: 3900990 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.6845. Min Act: -0.1700
Data Index: 5623479 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.7157. Min Act: -0.1700
Data Index: 880748 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.6845. Min Act: -0.1700
Data Index: 1808946 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.6845. Min Act: -0.1700
Data Index: 6514518 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.6532. Min Act: -0.1700
Data Index: 3557622 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9657. Min Range: -5.9657
Max Act: 5.6532. Min Act: -0.1700
Data Index: 7088907 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19