Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.6222. Min Act: -0.1700
Data Index: 4022297 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.5440. Min Act: -0.1700
Data Index: 3433866 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.5126. Min Act: -0.1700
Data Index: 5086535 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.4970. Min Act: -0.1700
Data Index: 1570544 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.4813. Min Act: -0.1700
Data Index: 5189593 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.4500. Min Act: -0.1700
Data Index: 2840880 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.4500. Min Act: -0.1700
Data Index: 7442291 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.4343. Min Act: -0.1700
Data Index: 7527959 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.4030. Min Act: -0.1700
Data Index: 2313559 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.4500. Min Act: -0.1700
Data Index: 2924149 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.4030. Min Act: -0.1700
Data Index: 8579938 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.4030. Min Act: -0.1700
Data Index: 1038967 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.3873. Min Act: -0.1700
Data Index: 7163938 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.3873. Min Act: -0.1700
Data Index: 2502629 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.3873. Min Act: -0.1700
Data Index: 8119207 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.3873. Min Act: -0.1700
Data Index: 3176881 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.3873. Min Act: -0.1700
Data Index: 6369516 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.3559. Min Act: -0.1700
Data Index: 3139540 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.3873. Min Act: -0.1700
Data Index: 4965415 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6222. Min Range: -3.6222
Max Act: 3.3873. Min Act: -0.1700
Data Index: 3246075 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19