Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.6726. Min Act: -0.1700
Data Index: 8224888 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.5788. Min Act: -0.1700
Data Index: 2534477 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.6101. Min Act: -0.1700
Data Index: 5049239 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.4851. Min Act: -0.1700
Data Index: 4160857 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.4851. Min Act: -0.1700
Data Index: 983363 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.3288. Min Act: -0.1700
Data Index: 6539818 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.3288. Min Act: -0.1700
Data Index: 376653 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.3601. Min Act: -0.1700
Data Index: 8583199 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.3288. Min Act: -0.1700
Data Index: 565892 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.2976. Min Act: -0.1700
Data Index: 8542064 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.2663. Min Act: -0.1700
Data Index: 7204986 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.1726. Min Act: -0.1700
Data Index: 1888466 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.1726. Min Act: -0.1700
Data Index: 3018290 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.1413. Min Act: -0.1700
Data Index: 404560 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.1413. Min Act: -0.1700
Data Index: 5914706 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.0476. Min Act: -0.1700
Data Index: 600653 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.0163. Min Act: -0.1700
Data Index: 3312555 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6726. Min Range: -6.6726
Max Act: 6.0163. Min Act: -0.1700
Data Index: 8563383 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6726. Min Range: -6.6726
Max Act: 5.9538. Min Act: -0.1700
Data Index: 2892384 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6726. Min Range: -6.6726
Max Act: 5.9851. Min Act: -0.1700
Data Index: 1214916 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19