Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.8876. Min Act: -0.1700
Data Index: 7358361 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.8876. Min Act: -0.1700
Data Index: 5113854 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.7626. Min Act: -0.1700
Data Index: 5918833 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.7626. Min Act: -0.1700
Data Index: 1324160 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.7001. Min Act: -0.1700
Data Index: 1811052 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.6376. Min Act: -0.1700
Data Index: 4292027 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.6376. Min Act: -0.1700
Data Index: 4090479 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.6376. Min Act: -0.1700
Data Index: 6405831 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.5751. Min Act: -0.1700
Data Index: 7489197 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.5751. Min Act: -0.1700
Data Index: 5874910 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.5126. Min Act: -0.1700
Data Index: 7338501 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.5126. Min Act: -0.1700
Data Index: 445531 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.5126. Min Act: -0.1700
Data Index: 539216 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.5126. Min Act: -0.1700
Data Index: 44581 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.5126. Min Act: -0.1700
Data Index: 7089979 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.5126. Min Act: -0.1700
Data Index: 7957538 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.5126. Min Act: -0.1700
Data Index: 2412196 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.4501. Min Act: -0.1700
Data Index: 7381114 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.4501. Min Act: -0.1700
Data Index: 3666772 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8876. Min Range: -8.8876
Max Act: 8.3876. Min Act: -0.1700
Data Index: 2932762 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19