Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3557 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.8386. Min Act: -0.1700
Data Index: 6853667 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.6196. Min Act: -0.1700
Data Index: 450838 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.6196. Min Act: -0.1700
Data Index: 6905050 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5883. Min Act: -0.1700
Data Index: 7869198 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5726. Min Act: -0.1700
Data Index: 8379557 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5726. Min Act: -0.1700
Data Index: 2966049 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5883. Min Act: -0.1700
Data Index: 8178509 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5257. Min Act: -0.1700
Data Index: 1000408 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5570. Min Act: -0.1700
Data Index: 8424911 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5257. Min Act: -0.1700
Data Index: 2874912 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5413. Min Act: -0.1700
Data Index: 6333832 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5257. Min Act: -0.1700
Data Index: 4886157 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5257. Min Act: -0.1700
Data Index: 6764860 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5257. Min Act: -0.1700
Data Index: 361500 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.4944. Min Act: -0.1700
Data Index: 8729035 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.4944. Min Act: -0.1700
Data Index: 6376187 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.4944. Min Act: -0.1700
Data Index: 6204798 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.5100. Min Act: -0.1700
Data Index: 2778038 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.4944. Min Act: -0.1700
Data Index: 3141168 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8386. Min Range: -3.8386
Max Act: 3.4944. Min Act: -0.1700
Data Index: 8497573 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19