Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 370 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.8541. Min Act: -0.1700
Data Index: 1412985 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.7916. Min Act: -0.1700
Data Index: 8764472 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.5729. Min Act: -0.1700
Data Index: 4521461 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.3541. Min Act: -0.1700
Data Index: 6757029 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1979. Min Act: -0.1700
Data Index: 5514443 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1666. Min Act: -0.1700
Data Index: 8688117 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1666. Min Act: -0.1700
Data Index: 7894872 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1666. Min Act: -0.1700
Data Index: 3190245 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1666. Min Act: -0.1700
Data Index: 6818192 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1354. Min Act: -0.1700
Data Index: 7838116 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1354. Min Act: -0.1700
Data Index: 1496971 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1041. Min Act: -0.1700
Data Index: 5983433 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1666. Min Act: -0.1700
Data Index: 141732 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1354. Min Act: -0.1700
Data Index: 3002514 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1354. Min Act: -0.1700
Data Index: 2908897 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.0729. Min Act: -0.1700
Data Index: 7969005 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1041. Min Act: -0.1700
Data Index: 8760364 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1041. Min Act: -0.1700
Data Index: 5717682 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.1041. Min Act: -0.1700
Data Index: 2374390 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8541. Min Range: -6.8541
Max Act: 6.0729. Min Act: -0.1700
Data Index: 3541869 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19