Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.3061. Min Act: -0.1700
Data Index: 4090072 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.3374. Min Act: -0.1700
Data Index: 2076847 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.2436. Min Act: -0.1700
Data Index: 4695584 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.2124. Min Act: -0.1700
Data Index: 587461 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.2124. Min Act: -0.1700
Data Index: 4919312 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.2124. Min Act: -0.1700
Data Index: 2738823 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.1811. Min Act: -0.1700
Data Index: 7575893 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.1186. Min Act: -0.1700
Data Index: 202410 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0874. Min Act: -0.1700
Data Index: 5145882 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0874. Min Act: -0.1700
Data Index: 575516 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0561. Min Act: -0.1700
Data Index: 7001375 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0874. Min Act: -0.1700
Data Index: 1115438 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0874. Min Act: -0.1700
Data Index: 5145881 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0561. Min Act: -0.1700
Data Index: 7616584 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0561. Min Act: -0.1700
Data Index: 5705430 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0249. Min Act: -0.1700
Data Index: 345822 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0249. Min Act: -0.1700
Data Index: 6451348 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0561. Min Act: -0.1700
Data Index: 646466 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0249. Min Act: -0.1700
Data Index: 202409 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3374. Min Range: -4.3374
Max Act: 4.0249. Min Act: -0.1700
Data Index: 6035093 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19