Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5568 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1351. Min Range: -6.1351
Max Act: 6.1351. Min Act: -0.1700
Data Index: 5780461 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1351. Min Range: -6.1351
Max Act: 6.0726. Min Act: -0.1700
Data Index: 7548145 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.9788. Min Act: -0.1700
Data Index: 2827726 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.9788. Min Act: -0.1700
Data Index: 5051960 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.9163. Min Act: -0.1700
Data Index: 917664 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.9163. Min Act: -0.1700
Data Index: 2778843 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.9163. Min Act: -0.1700
Data Index: 6183740 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.9163. Min Act: -0.1700
Data Index: 3358014 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.8538. Min Act: -0.1700
Data Index: 2769138 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.8226. Min Act: -0.1700
Data Index: 828766 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.8226. Min Act: -0.1700
Data Index: 2543056 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.8538. Min Act: -0.1700
Data Index: 4406938 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.7913. Min Act: -0.1700
Data Index: 3635730 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.7601. Min Act: -0.1700
Data Index: 4848415 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.7288. Min Act: -0.1700
Data Index: 8148811 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.7288. Min Act: -0.1700
Data Index: 1823807 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.7601. Min Act: -0.1700
Data Index: 4152163 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.7601. Min Act: -0.1700
Data Index: 7542676 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.6976. Min Act: -0.1700
Data Index: 6806888 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1351. Min Range: -6.1351
Max Act: 5.7288. Min Act: -0.1700
Data Index: 2799646 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19