Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1739. Min Range: -6.1739
Max Act: 6.1739. Min Act: -0.1700
Data Index: 8378491 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1739. Min Range: -6.1739
Max Act: 6.0176. Min Act: -0.1700
Data Index: 4411529 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1739. Min Range: -6.1739
Max Act: 6.0176. Min Act: -0.1700
Data Index: 4485933 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1739. Min Range: -6.1739
Max Act: 6.0176. Min Act: -0.1700
Data Index: 7468103 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.8614. Min Act: -0.1700
Data Index: 4199419 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.8301. Min Act: -0.1700
Data Index: 6047335 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.8301. Min Act: -0.1700
Data Index: 4054425 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7989. Min Act: -0.1700
Data Index: 937355 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7676. Min Act: -0.1700
Data Index: 2021527 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7676. Min Act: -0.1700
Data Index: 2334004 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7364. Min Act: -0.1700
Data Index: 6483629 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7051. Min Act: -0.1700
Data Index: 5899499 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7051. Min Act: -0.1700
Data Index: 1121317 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7051. Min Act: -0.1700
Data Index: 6489320 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7051. Min Act: -0.1700
Data Index: 1802665 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7051. Min Act: -0.1700
Data Index: 4948736 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7051. Min Act: -0.1700
Data Index: 2886810 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.7051. Min Act: -0.1700
Data Index: 7033549 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.6739. Min Act: -0.1700
Data Index: 570772 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1739. Min Range: -6.1739
Max Act: 5.6739. Min Act: -0.1700
Data Index: 6536234 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19