Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 759 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6137. Min Range: -8.6137
Max Act: 8.6137. Min Act: -0.1700
Data Index: 4927430 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6137. Min Range: -8.6137
Max Act: 8.4887. Min Act: -0.1700
Data Index: 5975152 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6137. Min Range: -8.6137
Max Act: 8.1762. Min Act: -0.1700
Data Index: 6859358 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6137. Min Range: -8.6137
Max Act: 8.0512. Min Act: -0.1700
Data Index: 4406249 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.9262. Min Act: -0.1700
Data Index: 7163660 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.9262. Min Act: -0.1700
Data Index: 5452259 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.9262. Min Act: -0.1700
Data Index: 2276939 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.9262. Min Act: -0.1700
Data Index: 1420338 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.9262. Min Act: -0.1700
Data Index: 4797308 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.8637. Min Act: -0.1700
Data Index: 2454581 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.8012. Min Act: -0.1700
Data Index: 5594870 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.8012. Min Act: -0.1700
Data Index: 7303884 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.7700. Min Act: -0.1700
Data Index: 7054047 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.8012. Min Act: -0.1700
Data Index: 5664159 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.7700. Min Act: -0.1700
Data Index: 1584219 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.7700. Min Act: -0.1700
Data Index: 1106077 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.7387. Min Act: -0.1700
Data Index: 2282103 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.7387. Min Act: -0.1700
Data Index: 7232468 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.7075. Min Act: -0.1700
Data Index: 4524075 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6137. Min Range: -8.6137
Max Act: 7.7075. Min Act: -0.1700
Data Index: 1085152 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19