Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0189. Min Range: -4.0189
Max Act: 4.0189. Min Act: -0.1700
Data Index: 8610144 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.8626. Min Act: -0.1700
Data Index: 4148912 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.8626. Min Act: -0.1700
Data Index: 6057484 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.8314. Min Act: -0.1700
Data Index: 294615 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.8626. Min Act: -0.1700
Data Index: 2538250 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.8001. Min Act: -0.1700
Data Index: 7823060 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.7688. Min Act: -0.1700
Data Index: 4656801 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.8001. Min Act: -0.1700
Data Index: 528483 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.7532. Min Act: -0.1700
Data Index: 4962419 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.7375. Min Act: -0.1700
Data Index: 1446963 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.7062. Min Act: -0.1700
Data Index: 3521124 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.6906. Min Act: -0.1700
Data Index: 7341648 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.6593. Min Act: -0.1700
Data Index: 4117607 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.6437. Min Act: -0.1700
Data Index: 7239658 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.6124. Min Act: -0.1700
Data Index: 2394191 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.6593. Min Act: -0.1700
Data Index: 8310211 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.6437. Min Act: -0.1700
Data Index: 7275880 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.6280. Min Act: -0.1700
Data Index: 4694149 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.5967. Min Act: -0.1700
Data Index: 7006679 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0189. Min Range: -4.0189
Max Act: 3.6124. Min Act: -0.1700
Data Index: 4194796 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19