Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1625 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6799. Min Range: -5.6799
Max Act: 5.6799. Min Act: -0.1700
Data Index: 6314716 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6799. Min Range: -5.6799
Max Act: 5.4299. Min Act: -0.1700
Data Index: 3108659 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6799. Min Range: -5.6799
Max Act: 5.4299. Min Act: -0.1700
Data Index: 6205257 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6799. Min Range: -5.6799
Max Act: 5.2424. Min Act: -0.1700
Data Index: 7298662 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6799. Min Range: -5.6799
Max Act: 5.0862. Min Act: -0.1700
Data Index: 8221530 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.9924. Min Act: -0.1700
Data Index: 1476117 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.9924. Min Act: -0.1700
Data Index: 5448245 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.9612. Min Act: -0.1700
Data Index: 4996920 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.9612. Min Act: -0.1700
Data Index: 7545122 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.9612. Min Act: -0.1700
Data Index: 5794543 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8987. Min Act: -0.1700
Data Index: 5634638 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8674. Min Act: -0.1700
Data Index: 1867091 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8987. Min Act: -0.1700
Data Index: 1818682 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8674. Min Act: -0.1700
Data Index: 5543597 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8674. Min Act: -0.1700
Data Index: 3024626 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8049. Min Act: -0.1700
Data Index: 2912896 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8362. Min Act: -0.1700
Data Index: 5269966 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8049. Min Act: -0.1700
Data Index: 1683506 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8049. Min Act: -0.1700
Data Index: 701509 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6799. Min Range: -5.6799
Max Act: 4.8049. Min Act: -0.1700
Data Index: 5220835 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19