Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6364 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.9509. Min Act: -0.1700
Data Index: 6278788 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.8884. Min Act: -0.1700
Data Index: 3791638 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.8884. Min Act: -0.1700
Data Index: 6289339 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.8259. Min Act: -0.1700
Data Index: 4064299 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.7634. Min Act: -0.1700
Data Index: 8269742 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.7634. Min Act: -0.1700
Data Index: 2422764 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.8259. Min Act: -0.1700
Data Index: 4967556 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.7634. Min Act: -0.1700
Data Index: 6733756 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.7634. Min Act: -0.1700
Data Index: 880031 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.7009. Min Act: -0.1700
Data Index: 3256497 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.7009. Min Act: -0.1700
Data Index: 7294220 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.7009. Min Act: -0.1700
Data Index: 4500953 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.7009. Min Act: -0.1700
Data Index: 505455 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.7009. Min Act: -0.1700
Data Index: 8553017 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.6384. Min Act: -0.1700
Data Index: 2184481 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.6384. Min Act: -0.1700
Data Index: 4348959 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.6384. Min Act: -0.1700
Data Index: 8027328 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.6384. Min Act: -0.1700
Data Index: 384534 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.6384. Min Act: -0.1700
Data Index: 8646377 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9509. Min Range: -8.9509
Max Act: 8.5759. Min Act: -0.1700
Data Index: 5527508 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19