Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3236 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.5653. Min Act: -0.1700
Data Index: 4748192 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.4715. Min Act: -0.1700
Data Index: 1928719 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.4403. Min Act: -0.1700
Data Index: 6407586 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.4403. Min Act: -0.1700
Data Index: 3247586 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.3778. Min Act: -0.1700
Data Index: 8313604 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.3465. Min Act: -0.1700
Data Index: 4322885 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.2840. Min Act: -0.1700
Data Index: 1379677 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.3153. Min Act: -0.1700
Data Index: 4095516 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.3153. Min Act: -0.1700
Data Index: 335150 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.3153. Min Act: -0.1700
Data Index: 2322279 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.2528. Min Act: -0.1700
Data Index: 3451672 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.2840. Min Act: -0.1700
Data Index: 2979140 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.2528. Min Act: -0.1700
Data Index: 2223785 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.2215. Min Act: -0.1700
Data Index: 1757789 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.2215. Min Act: -0.1700
Data Index: 4989093 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.2215. Min Act: -0.1700
Data Index: 1927972 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.2215. Min Act: -0.1700
Data Index: 5702799 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.1902. Min Act: -0.1700
Data Index: 3975982 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.1902. Min Act: -0.1700
Data Index: 5434999 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5653. Min Range: -4.5653
Max Act: 4.1590. Min Act: -0.1700
Data Index: 5606981 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19