Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2512 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.9377. Min Act: -0.1700
Data Index: 7512387 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.8127. Min Act: -0.1700
Data Index: 3535405 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.8127. Min Act: -0.1700
Data Index: 1113669 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.8127. Min Act: -0.1700
Data Index: 8610857 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.7502. Min Act: -0.1700
Data Index: 477647 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.7502. Min Act: -0.1700
Data Index: 3916843 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.7189. Min Act: -0.1700
Data Index: 3916847 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.7189. Min Act: -0.1700
Data Index: 2754260 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.6877. Min Act: -0.1700
Data Index: 7568090 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.6877. Min Act: -0.1700
Data Index: 3626194 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.6564. Min Act: -0.1700
Data Index: 7902389 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.6564. Min Act: -0.1700
Data Index: 6758664 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.6564. Min Act: -0.1700
Data Index: 2677136 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.6252. Min Act: -0.1700
Data Index: 7998068 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.6252. Min Act: -0.1700
Data Index: 3519931 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.5939. Min Act: -0.1700
Data Index: 5484090 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.5939. Min Act: -0.1700
Data Index: 6544485 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.5627. Min Act: -0.1700
Data Index: 1612578 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.5627. Min Act: -0.1700
Data Index: 6566227 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9377. Min Range: -7.9377
Max Act: 7.5002. Min Act: -0.1700
Data Index: 7007585 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19