Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4765 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.9477. Min Act: -0.1700
Data Index: 8463771 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.8227. Min Act: -0.1700
Data Index: 8133637 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.4165. Min Act: -0.1700
Data Index: 4411056 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.3227. Min Act: -0.1700
Data Index: 7688583 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.2602. Min Act: -0.1700
Data Index: 7703489 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.2290. Min Act: -0.1700
Data Index: 3116977 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.2602. Min Act: -0.1700
Data Index: 3687131 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.1665. Min Act: -0.1700
Data Index: 2041844 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.1352. Min Act: -0.1700
Data Index: 3840185 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.1352. Min Act: -0.1700
Data Index: 7658745 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.0727. Min Act: -0.1700
Data Index: 216454 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.0727. Min Act: -0.1700
Data Index: 3364115 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.0727. Min Act: -0.1700
Data Index: 6084300 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.0102. Min Act: -0.1700
Data Index: 6727261 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.0102. Min Act: -0.1700
Data Index: 8718180 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.0102. Min Act: -0.1700
Data Index: 1653541 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9477. Min Range: -7.9477
Max Act: 6.9790. Min Act: -0.1700
Data Index: 6336391 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9477. Min Range: -7.9477
Max Act: 6.9790. Min Act: -0.1700
Data Index: 959546 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9477. Min Range: -7.9477
Max Act: 6.9790. Min Act: -0.1700
Data Index: 6488428 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9477. Min Range: -7.9477
Max Act: 7.0102. Min Act: -0.1700
Data Index: 3677785 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19