Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1277. Min Range: -5.1277
Max Act: 5.1277. Min Act: -0.1700
Data Index: 4986751 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1277. Min Range: -5.1277
Max Act: 5.0652. Min Act: -0.1700
Data Index: 8773178 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.8152. Min Act: -0.1700
Data Index: 1931098 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.7839. Min Act: -0.1700
Data Index: 3285197 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.7839. Min Act: -0.1700
Data Index: 699934 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.7527. Min Act: -0.1700
Data Index: 3839456 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.7214. Min Act: -0.1700
Data Index: 5851251 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.6902. Min Act: -0.1700
Data Index: 534507 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.6902. Min Act: -0.1700
Data Index: 725120 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.6902. Min Act: -0.1700
Data Index: 258046 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.6589. Min Act: -0.1700
Data Index: 5301718 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.6277. Min Act: -0.1700
Data Index: 4306324 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.5964. Min Act: -0.1700
Data Index: 6711088 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.5652. Min Act: -0.1700
Data Index: 8533785 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.5652. Min Act: -0.1700
Data Index: 5811811 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.5339. Min Act: -0.1700
Data Index: 1678202 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.5339. Min Act: -0.1700
Data Index: 8668111 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.5339. Min Act: -0.1700
Data Index: 2778630 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.5027. Min Act: -0.1700
Data Index: 2022687 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1277. Min Range: -5.1277
Max Act: 4.5339. Min Act: -0.1700
Data Index: 3035200 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19