Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.9761. Min Act: -0.1700
Data Index: 1126082 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.7886. Min Act: -0.1700
Data Index: 3479701 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.6636. Min Act: -0.1700
Data Index: 3581095 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.4761. Min Act: -0.1700
Data Index: 3477047 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.4761. Min Act: -0.1700
Data Index: 4383660 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.4136. Min Act: -0.1700
Data Index: 2678699 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.4136. Min Act: -0.1700
Data Index: 3531156 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.4761. Min Act: -0.1700
Data Index: 7736272 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.3511. Min Act: -0.1700
Data Index: 4941387 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.2886. Min Act: -0.1700
Data Index: 1475922 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.2261. Min Act: -0.1700
Data Index: 3492138 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.2261. Min Act: -0.1700
Data Index: 7299411 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.2261. Min Act: -0.1700
Data Index: 4837577 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.1636. Min Act: -0.1700
Data Index: 389335 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.1636. Min Act: -0.1700
Data Index: 7328747 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.1636. Min Act: -0.1700
Data Index: 6921032 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.1636. Min Act: -0.1700
Data Index: 8626203 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.1011. Min Act: -0.1700
Data Index: 2461275 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.0699. Min Act: -0.1700
Data Index: 5058702 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9761. Min Range: -8.9761
Max Act: 8.0699. Min Act: -0.1700
Data Index: 5460711 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19