Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3072. Min Range: -6.3072
Max Act: 6.3072. Min Act: -0.1700
Data Index: 4982664 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3072. Min Range: -6.3072
Max Act: 6.3072. Min Act: -0.1700
Data Index: 2892202 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3072. Min Range: -6.3072
Max Act: 6.0572. Min Act: -0.1700
Data Index: 367314 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3072. Min Range: -6.3072
Max Act: 6.0260. Min Act: -0.1700
Data Index: 7686223 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9947. Min Act: -0.1700
Data Index: 5923245 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9947. Min Act: -0.1700
Data Index: 4037733 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9635. Min Act: -0.1700
Data Index: 6086561 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9635. Min Act: -0.1700
Data Index: 1755132 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9635. Min Act: -0.1700
Data Index: 6528195 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9322. Min Act: -0.1700
Data Index: 3355936 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9322. Min Act: -0.1700
Data Index: 5887829 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9010. Min Act: -0.1700
Data Index: 7071923 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9010. Min Act: -0.1700
Data Index: 7649476 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.8697. Min Act: -0.1700
Data Index: 6435629 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9010. Min Act: -0.1700
Data Index: 1032569 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9010. Min Act: -0.1700
Data Index: 3902400 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.9010. Min Act: -0.1700
Data Index: 3291461 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.8697. Min Act: -0.1700
Data Index: 4669792 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.8697. Min Act: -0.1700
Data Index: 4689557 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3072. Min Range: -6.3072
Max Act: 5.8697. Min Act: -0.1700
Data Index: 5342614 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19