Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3600 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.9711. Min Act: -0.1700
Data Index: 1139281 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0023. Min Range: -5.0023
Max Act: 5.0023. Min Act: -0.1700
Data Index: 697712 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.8148. Min Act: -0.1700
Data Index: 339507 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.8148. Min Act: -0.1700
Data Index: 8535747 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.7836. Min Act: -0.1700
Data Index: 1552888 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.6898. Min Act: -0.1700
Data Index: 7058323 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5961. Min Act: -0.1700
Data Index: 1981796 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5648. Min Act: -0.1700
Data Index: 4959134 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5648. Min Act: -0.1700
Data Index: 7674129 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5648. Min Act: -0.1700
Data Index: 1976811 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5648. Min Act: -0.1700
Data Index: 4003161 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5648. Min Act: -0.1700
Data Index: 6544198 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5023. Min Act: -0.1700
Data Index: 374217 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5023. Min Act: -0.1700
Data Index: 8539873 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5023. Min Act: -0.1700
Data Index: 2461486 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.4711. Min Act: -0.1700
Data Index: 292026 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5023. Min Act: -0.1700
Data Index: 3912878 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5023. Min Act: -0.1700
Data Index: 2488818 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.5336. Min Act: -0.1700
Data Index: 1337815 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0023. Min Range: -5.0023
Max Act: 4.4711. Min Act: -0.1700
Data Index: 8190654 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19