Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5673 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4583. Min Range: -8.4583
Max Act: 8.4583. Min Act: -0.1700
Data Index: 5084425 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4583. Min Range: -8.4583
Max Act: 8.3333. Min Act: -0.1700
Data Index: 2432683 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4583. Min Range: -8.4583
Max Act: 8.2708. Min Act: -0.1700
Data Index: 1785259 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4583. Min Range: -8.4583
Max Act: 8.2083. Min Act: -0.1700
Data Index: 1209642 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4583. Min Range: -8.4583
Max Act: 8.0833. Min Act: -0.1700
Data Index: 5135911 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4583. Min Range: -8.4583
Max Act: 8.0833. Min Act: -0.1700
Data Index: 4531449 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4583. Min Range: -8.4583
Max Act: 8.0208. Min Act: -0.1700
Data Index: 7783318 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4583. Min Range: -8.4583
Max Act: 8.0208. Min Act: -0.1700
Data Index: 5060111 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4583. Min Range: -8.4583
Max Act: 8.0208. Min Act: -0.1700
Data Index: 6034777 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.9583. Min Act: -0.1700
Data Index: 3567801 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.9583. Min Act: -0.1700
Data Index: 3882860 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.8958. Min Act: -0.1700
Data Index: 1374329 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.9583. Min Act: -0.1700
Data Index: 3625565 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.8958. Min Act: -0.1700
Data Index: 4669268 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.8958. Min Act: -0.1700
Data Index: 5635884 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.8333. Min Act: -0.1700
Data Index: 1219616 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.8333. Min Act: -0.1700
Data Index: 4687841 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.8021. Min Act: -0.1700
Data Index: 3603442 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.7708. Min Act: -0.1700
Data Index: 439125 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4583. Min Range: -8.4583
Max Act: 7.7396. Min Act: -0.1700
Data Index: 850665 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19