Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.4561. Min Act: -0.1700
Data Index: 4737702 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.2061. Min Act: -0.1700
Data Index: 2566706 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.1749. Min Act: -0.1700
Data Index: 5547797 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.1123. Min Act: -0.1700
Data Index: 8533527 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.1436. Min Act: -0.1700
Data Index: 4179860 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.1123. Min Act: -0.1700
Data Index: 1840146 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.0811. Min Act: -0.1700
Data Index: 4280648 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.0498. Min Act: -0.1700
Data Index: 4724975 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.0498. Min Act: -0.1700
Data Index: 6637522 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.0498. Min Act: -0.1700
Data Index: 3222481 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4561. Min Range: -4.4561
Max Act: 4.0186. Min Act: -0.1700
Data Index: 8755493 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4561. Min Range: -4.4561
Max Act: 3.9873. Min Act: -0.1700
Data Index: 2705091 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4561. Min Range: -4.4561
Max Act: 3.9560. Min Act: -0.1700
Data Index: 5436374 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4561. Min Range: -4.4561
Max Act: 3.9560. Min Act: -0.1700
Data Index: 6015030 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4561. Min Range: -4.4561
Max Act: 3.9560. Min Act: -0.1700
Data Index: 2078517 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4561. Min Range: -4.4561
Max Act: 3.9560. Min Act: -0.1700
Data Index: 7898002 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4561. Min Range: -4.4561
Max Act: 3.9248. Min Act: -0.1700
Data Index: 3716526 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4561. Min Range: -4.4561
Max Act: 3.9248. Min Act: -0.1700
Data Index: 192536 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4561. Min Range: -4.4561
Max Act: 3.8935. Min Act: -0.1700
Data Index: 5127307 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4561. Min Range: -4.4561
Max Act: 3.9248. Min Act: -0.1700
Data Index: 1860868 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19