Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1315 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.9536. Min Act: -0.1700
Data Index: 2810388 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.8286. Min Act: -0.1700
Data Index: 331246 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.7349. Min Act: -0.1700
Data Index: 4427832 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.7349. Min Act: -0.1700
Data Index: 8813400 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.7036. Min Act: -0.1700
Data Index: 6872649 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.6411. Min Act: -0.1700
Data Index: 2712034 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.6411. Min Act: -0.1700
Data Index: 3340786 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.6411. Min Act: -0.1700
Data Index: 8294551 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.6099. Min Act: -0.1700
Data Index: 6362244 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.6099. Min Act: -0.1700
Data Index: 478015 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.6099. Min Act: -0.1700
Data Index: 5958269 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.5786. Min Act: -0.1700
Data Index: 6984994 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.5474. Min Act: -0.1700
Data Index: 606929 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.5474. Min Act: -0.1700
Data Index: 1808930 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.5474. Min Act: -0.1700
Data Index: 922207 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.5474. Min Act: -0.1700
Data Index: 7533777 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.5474. Min Act: -0.1700
Data Index: 774785 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.5474. Min Act: -0.1700
Data Index: 370225 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.5474. Min Act: -0.1700
Data Index: 6470018 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9536. Min Range: -4.9536
Max Act: 4.4849. Min Act: -0.1700
Data Index: 7601476 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19