Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3152 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3083. Min Range: -8.3083
Max Act: 8.3083. Min Act: -0.1700
Data Index: 3836414 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.9958. Min Act: -0.1700
Data Index: 2934873 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.9958. Min Act: -0.1700
Data Index: 2102540 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.9333. Min Act: -0.1700
Data Index: 3004176 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.9333. Min Act: -0.1700
Data Index: 7558066 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.8708. Min Act: -0.1700
Data Index: 222863 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.8708. Min Act: -0.1700
Data Index: 2765124 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.8083. Min Act: -0.1700
Data Index: 189007 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.8083. Min Act: -0.1700
Data Index: 929628 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.8083. Min Act: -0.1700
Data Index: 687294 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.8083. Min Act: -0.1700
Data Index: 5551673 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.7458. Min Act: -0.1700
Data Index: 4983877 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.7458. Min Act: -0.1700
Data Index: 4275129 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.8083. Min Act: -0.1700
Data Index: 3282778 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.7458. Min Act: -0.1700
Data Index: 4279981 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.7458. Min Act: -0.1700
Data Index: 7967846 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.6833. Min Act: -0.1700
Data Index: 189106 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.6833. Min Act: -0.1700
Data Index: 1469610 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.6833. Min Act: -0.1700
Data Index: 6635902 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3083. Min Range: -8.3083
Max Act: 7.6833. Min Act: -0.1700
Data Index: 1724216 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19