Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 107 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.2694. Min Act: -0.1700
Data Index: 8395760 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.2069. Min Act: -0.1700
Data Index: 2293534 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.2069. Min Act: -0.1700
Data Index: 7233388 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1444. Min Act: -0.1700
Data Index: 7051947 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1444. Min Act: -0.1700
Data Index: 4926285 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1444. Min Act: -0.1700
Data Index: 390214 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1444. Min Act: -0.1700
Data Index: 2030418 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1444. Min Act: -0.1700
Data Index: 108601 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1444. Min Act: -0.1700
Data Index: 1648838 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1132. Min Act: -0.1700
Data Index: 1830349 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1132. Min Act: -0.1700
Data Index: 383559 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1132. Min Act: -0.1700
Data Index: 173869 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1132. Min Act: -0.1700
Data Index: 4069223 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1132. Min Act: -0.1700
Data Index: 447114 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1132. Min Act: -0.1700
Data Index: 6176520 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1132. Min Act: -0.1700
Data Index: 4960347 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.0819. Min Act: -0.1700
Data Index: 3807161 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.1132. Min Act: -0.1700
Data Index: 3847509 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.0819. Min Act: -0.1700
Data Index: 4179707 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2694. Min Range: -5.2694
Max Act: 5.0819. Min Act: -0.1700
Data Index: 1097608 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19