Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0124. Min Range: -8.0124
Max Act: 8.0124. Min Act: -0.1700
Data Index: 587418 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.5124. Min Act: -0.1700
Data Index: 1213464 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.4499. Min Act: -0.1700
Data Index: 298971 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.5124. Min Act: -0.1700
Data Index: 6727605 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.3561. Min Act: -0.1700
Data Index: 1403847 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.3561. Min Act: -0.1700
Data Index: 8076059 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.3561. Min Act: -0.1700
Data Index: 1403846 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.3249. Min Act: -0.1700
Data Index: 7400171 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.2936. Min Act: -0.1700
Data Index: 1430823 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.1686. Min Act: -0.1700
Data Index: 6726571 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.2311. Min Act: -0.1700
Data Index: 7400170 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.1686. Min Act: -0.1700
Data Index: 2663156 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.0749. Min Act: -0.1700
Data Index: 4825119 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.0124. Min Act: -0.1700
Data Index: 1213459 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0124. Min Range: -8.0124
Max Act: 6.9811. Min Act: -0.1700
Data Index: 5667673 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0124. Min Range: -8.0124
Max Act: 6.9811. Min Act: -0.1700
Data Index: 6159641 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0124. Min Range: -8.0124
Max Act: 6.9811. Min Act: -0.1700
Data Index: 860060 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0124. Min Range: -8.0124
Max Act: 6.9811. Min Act: -0.1700
Data Index: 7347389 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.0436. Min Act: -0.1700
Data Index: 217054 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0124. Min Range: -8.0124
Max Act: 7.0124. Min Act: -0.1700
Data Index: 6077426 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19