Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2680 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1351. Min Range: -8.1351
Max Act: 8.1351. Min Act: -0.1700
Data Index: 824273 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.8538. Min Act: -0.1700
Data Index: 4263980 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.8538. Min Act: -0.1700
Data Index: 3945804 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.7913. Min Act: -0.1700
Data Index: 7137189 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.7913. Min Act: -0.1700
Data Index: 4550849 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.7601. Min Act: -0.1700
Data Index: 8046471 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.7288. Min Act: -0.1700
Data Index: 8038796 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.6976. Min Act: -0.1700
Data Index: 995472 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.6976. Min Act: -0.1700
Data Index: 3061266 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.6351. Min Act: -0.1700
Data Index: 8042118 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.5726. Min Act: -0.1700
Data Index: 1412332 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.6038. Min Act: -0.1700
Data Index: 6977725 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.5413. Min Act: -0.1700
Data Index: 5306100 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.5413. Min Act: -0.1700
Data Index: 6745791 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.5101. Min Act: -0.1700
Data Index: 4917773 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.5101. Min Act: -0.1700
Data Index: 7685292 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.5101. Min Act: -0.1700
Data Index: 2163756 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.4788. Min Act: -0.1700
Data Index: 7105791 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.4788. Min Act: -0.1700
Data Index: 2356132 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1351. Min Range: -8.1351
Max Act: 7.4788. Min Act: -0.1700
Data Index: 3812567 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19