Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5702 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.2538. Min Act: -0.1700
Data Index: 243219 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.2226. Min Act: -0.1700
Data Index: 8453754 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.2538. Min Act: -0.1700
Data Index: 6809878 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.1913. Min Act: -0.1700
Data Index: 8292507 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.1913. Min Act: -0.1700
Data Index: 6842258 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.1288. Min Act: -0.1700
Data Index: 435058 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.1288. Min Act: -0.1700
Data Index: 5405409 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.0976. Min Act: -0.1700
Data Index: 3357907 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.0663. Min Act: -0.1700
Data Index: 4027374 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.0351. Min Act: -0.1700
Data Index: 2321274 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.0351. Min Act: -0.1699
Data Index: 3068894 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2538. Min Range: -6.2538
Max Act: 6.0038. Min Act: -0.1700
Data Index: 8756532 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2538. Min Range: -6.2538
Max Act: 5.9726. Min Act: -0.1700
Data Index: 2321285 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2538. Min Range: -6.2538
Max Act: 5.9726. Min Act: -0.1700
Data Index: 4439573 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2538. Min Range: -6.2538
Max Act: 5.9726. Min Act: -0.1700
Data Index: 298835 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2538. Min Range: -6.2538
Max Act: 5.9726. Min Act: -0.1700
Data Index: 3455330 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2538. Min Range: -6.2538
Max Act: 5.9726. Min Act: -0.1700
Data Index: 4376953 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2538. Min Range: -6.2538
Max Act: 5.9726. Min Act: -0.1700
Data Index: 4747296 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2538. Min Range: -6.2538
Max Act: 5.9413. Min Act: -0.1700
Data Index: 1111955 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2538. Min Range: -6.2538
Max Act: 5.9413. Min Act: -0.1700
Data Index: 1954666 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19