Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.3185. Min Act: -0.1700
Data Index: 6777552 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.2872. Min Act: -0.1700
Data Index: 656294 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.2872. Min Act: -0.1700
Data Index: 1774029 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.2872. Min Act: -0.1700
Data Index: 8621719 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 3585845 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1622. Min Act: -0.1700
Data Index: 271270 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.1310. Min Act: -0.1700
Data Index: 2426822 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0997. Min Act: -0.1700
Data Index: 1435962 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0685. Min Act: -0.1700
Data Index: 5550584 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0685. Min Act: -0.1700
Data Index: 7083119 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0372. Min Act: -0.1700
Data Index: 8523214 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0372. Min Act: -0.1700
Data Index: 8523184 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0372. Min Act: -0.1700
Data Index: 8137096 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0685. Min Act: -0.1700
Data Index: 2426824 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0372. Min Act: -0.1700
Data Index: 2426820 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0060. Min Act: -0.1700
Data Index: 2295999 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0060. Min Act: -0.1700
Data Index: 276012 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3185. Min Range: -5.3185
Max Act: 5.0060. Min Act: -0.1700
Data Index: 1774038 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3185. Min Range: -5.3185
Max Act: 4.9747. Min Act: -0.1700
Data Index: 2976901 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3185. Min Range: -5.3185
Max Act: 4.9435. Min Act: -0.1700
Data Index: 2482998 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19