Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0783. Min Range: -5.0783
Max Act: 5.0783. Min Act: -0.1700
Data Index: 1301280 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0783. Min Range: -5.0783
Max Act: 5.0158. Min Act: -0.1700
Data Index: 6341310 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0783. Min Range: -5.0783
Max Act: 5.0158. Min Act: -0.1700
Data Index: 1120419 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.9533. Min Act: -0.1700
Data Index: 5681321 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.8908. Min Act: -0.1700
Data Index: 359976 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.8908. Min Act: -0.1700
Data Index: 5815024 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.8596. Min Act: -0.1700
Data Index: 8180604 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.8596. Min Act: -0.1700
Data Index: 5629510 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.8283. Min Act: -0.1700
Data Index: 5268945 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7971. Min Act: -0.1700
Data Index: 6914976 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7658. Min Act: -0.1700
Data Index: 6815300 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7658. Min Act: -0.1700
Data Index: 7007677 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7658. Min Act: -0.1700
Data Index: 1902396 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7346. Min Act: -0.1700
Data Index: 243405 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7346. Min Act: -0.1700
Data Index: 2713329 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7346. Min Act: -0.1700
Data Index: 4238846 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7033. Min Act: -0.1700
Data Index: 5266602 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7033. Min Act: -0.1700
Data Index: 5861535 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.7033. Min Act: -0.1700
Data Index: 498963 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0783. Min Range: -5.0783
Max Act: 4.6721. Min Act: -0.1700
Data Index: 1145150 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19