Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3940 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.7625. Min Act: -0.1700
Data Index: 6248795 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.5750. Min Act: -0.1700
Data Index: 7485176 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.4500. Min Act: -0.1700
Data Index: 4022103 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.3250. Min Act: -0.1700
Data Index: 6658339 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.3250. Min Act: -0.1700
Data Index: 7145048 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.2937. Min Act: -0.1700
Data Index: 8810680 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.2625. Min Act: -0.1700
Data Index: 2288585 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.2937. Min Act: -0.1700
Data Index: 6459119 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.2000. Min Act: -0.1700
Data Index: 2042672 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1687. Min Act: -0.1700
Data Index: 6446491 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1375. Min Act: -0.1700
Data Index: 1612555 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1375. Min Act: -0.1700
Data Index: 6091511 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1375. Min Act: -0.1700
Data Index: 775853 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1375. Min Act: -0.1700
Data Index: 5970411 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1375. Min Act: -0.1700
Data Index: 7465470 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1375. Min Act: -0.1700
Data Index: 6772137 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1375. Min Act: -0.1700
Data Index: 7582874 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1375. Min Act: -0.1700
Data Index: 7696890 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.1687. Min Act: -0.1700
Data Index: 4237525 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7625. Min Range: -5.7625
Max Act: 5.0750. Min Act: -0.1700
Data Index: 4001291 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19