Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 771 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.8132. Min Act: -0.1700
Data Index: 3149213 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5632. Min Act: -0.1700
Data Index: 6146186 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5319. Min Act: -0.1700
Data Index: 6525073 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.4694. Min Act: -0.1700
Data Index: 6819983 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5007. Min Act: -0.1700
Data Index: 2786562 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.4382. Min Act: -0.1700
Data Index: 4884038 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.4069. Min Act: -0.1700
Data Index: 2097842 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.3132. Min Act: -0.1700
Data Index: 5209685 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.3132. Min Act: -0.1700
Data Index: 3160039 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.3132. Min Act: -0.1700
Data Index: 4179496 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.2507. Min Act: -0.1700
Data Index: 8170598 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.2194. Min Act: -0.1700
Data Index: 6316961 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.2194. Min Act: -0.1700
Data Index: 7991584 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.1882. Min Act: -0.1700
Data Index: 6736228 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.1882. Min Act: -0.1700
Data Index: 1866628 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.1882. Min Act: -0.1700
Data Index: 3837551 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.1569. Min Act: -0.1700
Data Index: 7192148 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.1257. Min Act: -0.1700
Data Index: 1163753 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.1569. Min Act: -0.1700
Data Index: 511497 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.1257. Min Act: -0.1700
Data Index: 1045061 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19