Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1233 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.9920. Min Act: -0.1700
Data Index: 908628 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.8670. Min Act: -0.1700
Data Index: 8250946 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.8045. Min Act: -0.1700
Data Index: 3179457 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.7732. Min Act: -0.1700
Data Index: 3152256 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.7420. Min Act: -0.1700
Data Index: 8250948 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.7420. Min Act: -0.1700
Data Index: 4151418 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.7732. Min Act: -0.1700
Data Index: 245008 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.6170. Min Act: -0.1700
Data Index: 5263850 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.5857. Min Act: -0.1700
Data Index: 7333830 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.5857. Min Act: -0.1700
Data Index: 8430678 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.5857. Min Act: -0.1700
Data Index: 6990040 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.5232. Min Act: -0.1700
Data Index: 3739673 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.5857. Min Act: -0.1700
Data Index: 986731 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.5545. Min Act: -0.1700
Data Index: 762529 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.4920. Min Act: -0.1700
Data Index: 8708208 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.4920. Min Act: -0.1700
Data Index: 52382 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.4920. Min Act: -0.1700
Data Index: 871569 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.4920. Min Act: -0.1700
Data Index: 5659019 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.4607. Min Act: -0.1700
Data Index: 2925028 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9920. Min Range: -6.9920
Max Act: 6.4607. Min Act: -0.1700
Data Index: 7927107 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19