Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0264. Min Range: -4.0264
Max Act: 4.0264. Min Act: -0.1700
Data Index: 3179059 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.9951. Min Act: -0.1700
Data Index: 3557184 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.9951. Min Act: -0.1700
Data Index: 2065740 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.9326. Min Act: -0.1700
Data Index: 7330917 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.9013. Min Act: -0.1700
Data Index: 4274601 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.9013. Min Act: -0.1700
Data Index: 5172594 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8701. Min Act: -0.1700
Data Index: 2510675 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.9013. Min Act: -0.1700
Data Index: 7288462 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8701. Min Act: -0.1700
Data Index: 3089041 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8701. Min Act: -0.1700
Data Index: 5808736 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8701. Min Act: -0.1700
Data Index: 4695652 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8388. Min Act: -0.1700
Data Index: 6076959 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8701. Min Act: -0.1700
Data Index: 2954056 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8075. Min Act: -0.1700
Data Index: 384469 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8388. Min Act: -0.1700
Data Index: 5079989 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8075. Min Act: -0.1700
Data Index: 4965735 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8075. Min Act: -0.1700
Data Index: 2016578 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.7762. Min Act: -0.1700
Data Index: 3577911 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8075. Min Act: -0.1700
Data Index: 4521374 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0264. Min Range: -4.0264
Max Act: 3.8075. Min Act: -0.1700
Data Index: 2646196 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19