Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3300 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6833. Min Act: -0.1700
Data Index: 2904811 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5896. Min Act: -0.1700
Data Index: 2125893 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4958. Min Act: -0.1700
Data Index: 3241657 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4646. Min Act: -0.1700
Data Index: 2553251 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4646. Min Act: -0.1700
Data Index: 6219109 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4021. Min Act: -0.1700
Data Index: 7354546 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3708. Min Act: -0.1700
Data Index: 6349970 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3396. Min Act: -0.1700
Data Index: 1170634 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3396. Min Act: -0.1700
Data Index: 7573349 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2771. Min Act: -0.1700
Data Index: 3963177 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2146. Min Act: -0.1700
Data Index: 7204397 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.1833. Min Act: -0.1700
Data Index: 4545716 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.2146. Min Act: -0.1700
Data Index: 5466625 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.1833. Min Act: -0.1700
Data Index: 913523 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.1521. Min Act: -0.1700
Data Index: 3241665 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.1521. Min Act: -0.1700
Data Index: 1401806 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.1208. Min Act: -0.1700
Data Index: 952193 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.1521. Min Act: -0.1700
Data Index: 4858427 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.1521. Min Act: -0.1700
Data Index: 4089766 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.1521. Min Act: -0.1700
Data Index: 3336247 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19