Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2375 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1211. Min Range: -9.1211
Max Act: 9.1211. Min Act: -0.1700
Data Index: 6604800 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1211. Min Range: -9.1211
Max Act: 9.0586. Min Act: -0.1700
Data Index: 1266566 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.9961. Min Act: -0.1700
Data Index: 2186291 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.9961. Min Act: -0.1700
Data Index: 5160257 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.9336. Min Act: -0.1700
Data Index: 4421765 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.8711. Min Act: -0.1700
Data Index: 4641969 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.8086. Min Act: -0.1700
Data Index: 3098423 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.8086. Min Act: -0.1700
Data Index: 4201747 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.7461. Min Act: -0.1700
Data Index: 3594863 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.7461. Min Act: -0.1700
Data Index: 5608859 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.7461. Min Act: -0.1700
Data Index: 4791964 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6836. Min Act: -0.1700
Data Index: 3008793 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6836. Min Act: -0.1700
Data Index: 1332469 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6836. Min Act: -0.1700
Data Index: 4412806 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6211. Min Act: -0.1700
Data Index: 7614392 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6836. Min Act: -0.1700
Data Index: 4174666 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6211. Min Act: -0.1700
Data Index: 3053210 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6211. Min Act: -0.1700
Data Index: 4429876 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6211. Min Act: -0.1700
Data Index: 4511323 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1211. Min Range: -9.1211
Max Act: 8.6211. Min Act: -0.1700
Data Index: 2187599 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19