Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.8368. Min Act: -0.1700
Data Index: 2553394 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.8055. Min Act: -0.1700
Data Index: 5079731 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2055027 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2986119 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2986124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 698613 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 666768 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2852861 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 64223 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2125202 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 578210 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2542961 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 119674 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 1962442 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 1299437 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 970540 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 116736 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 2320010 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 1918926 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8368. Min Range: -3.8368
Max Act: 3.7742. Min Act: -0.1700
Data Index: 1902451 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19