Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0833. Min Range: -7.0833
Max Act: 7.0833. Min Act: -0.1700
Data Index: 705717 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0833. Min Range: -7.0833
Max Act: 7.0833. Min Act: -0.1700
Data Index: 3855799 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.9583. Min Act: -0.1700
Data Index: 1378073 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.9270. Min Act: -0.1700
Data Index: 1638731 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.8958. Min Act: -0.1700
Data Index: 468722 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.8645. Min Act: -0.1700
Data Index: 7619228 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.8020. Min Act: -0.1700
Data Index: 3675017 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.7395. Min Act: -0.1700
Data Index: 7737923 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.7395. Min Act: -0.1700
Data Index: 6490608 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.7083. Min Act: -0.1700
Data Index: 8649362 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.7083. Min Act: -0.1700
Data Index: 5089250 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.7083. Min Act: -0.1700
Data Index: 1740383 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.6458. Min Act: -0.1700
Data Index: 2032598 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.6458. Min Act: -0.1700
Data Index: 1380113 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.6458. Min Act: -0.1700
Data Index: 1729998 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.6145. Min Act: -0.1700
Data Index: 3753607 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.6145. Min Act: -0.1700
Data Index: 3395923 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.5833. Min Act: -0.1700
Data Index: 842557 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.5520. Min Act: -0.1700
Data Index: 6362483 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0833. Min Range: -7.0833
Max Act: 6.5833. Min Act: -0.1700
Data Index: 5189802 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19