Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3308. Min Range: -4.3308
Max Act: 4.3308. Min Act: -0.1700
Data Index: 8002737 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3308. Min Range: -4.3308
Max Act: 4.1120. Min Act: -0.1700
Data Index: 2460090 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.8306. Min Act: -0.1700
Data Index: 3485336 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.8306. Min Act: -0.1700
Data Index: 8820290 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.7681. Min Act: -0.1700
Data Index: 733719 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.7681. Min Act: -0.1700
Data Index: 2103993 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.6429. Min Act: -0.1700
Data Index: 1409574 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.6742. Min Act: -0.1700
Data Index: 6955809 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.6429. Min Act: -0.1700
Data Index: 5966131 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.6273. Min Act: -0.1700
Data Index: 4051677 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.6273. Min Act: -0.1700
Data Index: 8493557 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.5960. Min Act: -0.1700
Data Index: 5693127 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.5803. Min Act: -0.1700
Data Index: 2451232 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.5647. Min Act: -0.1700
Data Index: 5107086 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.5490. Min Act: -0.1700
Data Index: 8657188 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.5490. Min Act: -0.1700
Data Index: 3993257 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.5334. Min Act: -0.1700
Data Index: 6227007 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.5334. Min Act: -0.1700
Data Index: 5261135 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.5334. Min Act: -0.1700
Data Index: 2907249 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3308. Min Range: -4.3308
Max Act: 3.5334. Min Act: -0.1700
Data Index: 2016891 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19