Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1722 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.8054. Min Act: -0.1700
Data Index: 4170077 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.7742. Min Act: -0.1700
Data Index: 7358513 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.7117. Min Act: -0.1700
Data Index: 6974266 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.6179. Min Act: -0.1700
Data Index: 7235935 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.5867. Min Act: -0.1700
Data Index: 3700278 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.5867. Min Act: -0.1700
Data Index: 7057060 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.4617. Min Act: -0.1700
Data Index: 3269913 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.3367. Min Act: -0.1700
Data Index: 8757700 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.3992. Min Act: -0.1700
Data Index: 1115869 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.3054. Min Act: -0.1700
Data Index: 1595355 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.2742. Min Act: -0.1700
Data Index: 6699794 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.1804. Min Act: -0.1700
Data Index: 6278509 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.1804. Min Act: -0.1700
Data Index: 7683529 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.1179. Min Act: -0.1700
Data Index: 270829 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.1804. Min Act: -0.1700
Data Index: 1387008 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.0867. Min Act: -0.1700
Data Index: 7066837 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.1492. Min Act: -0.1700
Data Index: 2682340 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.1179. Min Act: -0.1700
Data Index: 6223068 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.1179. Min Act: -0.1700
Data Index: 7193555 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8054. Min Range: -7.8054
Max Act: 7.0554. Min Act: -0.1700
Data Index: 7073619 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19