Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1381 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.3561. Min Act: -0.1700
Data Index: 7301302 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.3561. Min Act: -0.1700
Data Index: 6903064 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.3248. Min Act: -0.1700
Data Index: 7301316 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.3248. Min Act: -0.1700
Data Index: 3111296 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.3248. Min Act: -0.1700
Data Index: 7921060 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2934. Min Act: -0.1700
Data Index: 5952031 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.3248. Min Act: -0.1700
Data Index: 8370329 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2934. Min Act: -0.1700
Data Index: 5876940 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2934. Min Act: -0.1700
Data Index: 711804 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2934. Min Act: -0.1700
Data Index: 8056091 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2934. Min Act: -0.1700
Data Index: 5994295 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2620. Min Act: -0.1700
Data Index: 5594713 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2620. Min Act: -0.1700
Data Index: 2446395 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2620. Min Act: -0.1700
Data Index: 1902031 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2620. Min Act: -0.1700
Data Index: 5994296 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2620. Min Act: -0.1700
Data Index: 7468464 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2463. Min Act: -0.1700
Data Index: 5440559 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2463. Min Act: -0.1700
Data Index: 7184353 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2463. Min Act: -0.1700
Data Index: 7129710 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3561. Min Range: -3.3561
Max Act: 3.2463. Min Act: -0.1700
Data Index: 3844931 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19