Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 871 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.5120. Min Act: -0.1700
Data Index: 1637835 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.5045. Min Act: -0.1688
Data Index: 3857305 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.5045. Min Act: -0.1698
Data Index: 8463726 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4820. Min Act: -0.1698
Data Index: 3313185 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4820. Min Act: -0.1695
Data Index: 1442383 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4895. Min Act: -0.1688
Data Index: 1650610 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4746. Min Act: -0.1684
Data Index: 4352262 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4672. Min Act: -0.1700
Data Index: 3273455 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4672. Min Act: -0.1700
Data Index: 2458530 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4746. Min Act: -0.1700
Data Index: 5596811 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4746. Min Act: -0.1700
Data Index: 4148658 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4672. Min Act: -0.1698
Data Index: 1388408 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4672. Min Act: -0.1700
Data Index: 5959955 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4672. Min Act: -0.1690
Data Index: 5793575 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4599. Min Act: -0.1693
Data Index: 3515423 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4599. Min Act: -0.1684
Data Index: 5065419 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4525. Min Act: -0.1700
Data Index: 4338174 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4452. Min Act: -0.1700
Data Index: 3460679 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4380. Min Act: -0.1656
Data Index: 5574925 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5120. Min Range: -0.5120
Max Act: 0.4380. Min Act: -0.1699
Data Index: 1522629 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19