Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4764 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6760. Min Range: -11.6760
Max Act: 11.6760. Min Act: -0.1700
Data Index: 4189462 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6760. Min Range: -11.6760
Max Act: 11.4260. Min Act: -0.1700
Data Index: 890958 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6760. Min Range: -11.6760
Max Act: 11.1135. Min Act: -0.1700
Data Index: 606719 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6760. Min Range: -11.6760
Max Act: 11.0510. Min Act: -0.1700
Data Index: 3793600 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.9260. Min Act: -0.1700
Data Index: 886619 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.9885. Min Act: -0.1700
Data Index: 1946419 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.9260. Min Act: -0.1700
Data Index: 3589723 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.8635. Min Act: -0.1700
Data Index: 4163533 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.8635. Min Act: -0.1700
Data Index: 2469221 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.8635. Min Act: -0.1700
Data Index: 5030915 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.8635. Min Act: -0.1700
Data Index: 5089194 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.8010. Min Act: -0.1700
Data Index: 6927773 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.7385. Min Act: -0.1700
Data Index: 4522622 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.7385. Min Act: -0.1700
Data Index: 3252234 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.6760. Min Act: -0.1700
Data Index: 862531 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.7385. Min Act: -0.1700
Data Index: 566785 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.6760. Min Act: -0.1700
Data Index: 2725691 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.6760. Min Act: -0.1700
Data Index: 1465943 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.6760. Min Act: -0.1700
Data Index: 1907093 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6760. Min Range: -11.6760
Max Act: 10.6760. Min Act: -0.1700
Data Index: 1674243 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19