Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1881 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.1199. Min Act: -0.1700
Data Index: 5445058 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0887. Min Act: -0.1700
Data Index: 6053204 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.1199. Min Act: -0.1700
Data Index: 2640466 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0887. Min Act: -0.1699
Data Index: 3904809 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0574. Min Act: -0.1700
Data Index: 2646125 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0887. Min Act: -0.1700
Data Index: 3833591 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0887. Min Act: -0.1700
Data Index: 8815387 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0887. Min Act: -0.1700
Data Index: 3103440 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0574. Min Act: -0.1700
Data Index: 8815384 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0262. Min Act: -0.1700
Data Index: 8291731 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0262. Min Act: -0.1700
Data Index: 5721096 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0262. Min Act: -0.1700
Data Index: 2640467 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0262. Min Act: -0.1700
Data Index: 7067656 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0262. Min Act: -0.1700
Data Index: 3904804 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1199. Min Range: -5.1199
Max Act: 5.0262. Min Act: -0.1700
Data Index: 543958 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1199. Min Range: -5.1199
Max Act: 4.9949. Min Act: -0.1700
Data Index: 3103441 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1199. Min Range: -5.1199
Max Act: 4.9949. Min Act: -0.1700
Data Index: 3689637 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1199. Min Range: -5.1199
Max Act: 4.9949. Min Act: -0.1700
Data Index: 2153460 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1199. Min Range: -5.1199
Max Act: 4.9637. Min Act: -0.1700
Data Index: 6589486 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1199. Min Range: -5.1199
Max Act: 4.9637. Min Act: -0.1700
Data Index: 3950052 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19