Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 903 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.7604. Min Act: -0.1700
Data Index: 1941595 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.6040. Min Act: -0.1700
Data Index: 1421022 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.6040. Min Act: -0.1700
Data Index: 4189325 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.6040. Min Act: -0.1700
Data Index: 998750 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.5727. Min Act: -0.1700
Data Index: 3775319 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.5413. Min Act: -0.1700
Data Index: 1091112 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.5100. Min Act: -0.1700
Data Index: 8432504 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.5100. Min Act: -0.1700
Data Index: 1421021 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.5100. Min Act: -0.1700
Data Index: 1421023 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.5413. Min Act: -0.1700
Data Index: 1421020 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.4787. Min Act: -0.1700
Data Index: 1011214 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.4474. Min Act: -0.1700
Data Index: 1421024 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.4474. Min Act: -0.1700
Data Index: 7031216 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.4787. Min Act: -0.1700
Data Index: 7231344 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.4474. Min Act: -0.1700
Data Index: 3327195 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.4474. Min Act: -0.1700
Data Index: 2963637 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.3847. Min Act: -0.1700
Data Index: 990662 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.4160. Min Act: -0.1700
Data Index: 5422401 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.3847. Min Act: -0.1700
Data Index: 4004330 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7604. Min Range: -3.7604
Max Act: 3.3847. Min Act: -0.1700
Data Index: 6796287 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19