Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2666 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.5253. Min Act: -0.1700
Data Index: 3551620 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.4628. Min Act: -0.1700
Data Index: 3847434 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.4316. Min Act: -0.1700
Data Index: 3305094 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.4003. Min Act: -0.1700
Data Index: 2704270 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.4003. Min Act: -0.1700
Data Index: 7713083 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.4003. Min Act: -0.1700
Data Index: 7948917 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.4003. Min Act: -0.1700
Data Index: 4650655 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.3378. Min Act: -0.1700
Data Index: 8695577 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.3378. Min Act: -0.1700
Data Index: 1293037 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.3066. Min Act: -0.1700
Data Index: 8083652 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.3066. Min Act: -0.1700
Data Index: 7978362 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.3066. Min Act: -0.1700
Data Index: 4841634 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2441. Min Act: -0.1700
Data Index: 5193887 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2441. Min Act: -0.1700
Data Index: 4005913 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.2128. Min Act: -0.1700
Data Index: 7478400 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1816. Min Act: -0.1700
Data Index: 5863872 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1503. Min Act: -0.1700
Data Index: 6116779 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1816. Min Act: -0.1700
Data Index: 5376117 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1816. Min Act: -0.1700
Data Index: 2216933 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5253. Min Range: -5.5253
Max Act: 5.1503. Min Act: -0.1700
Data Index: 6400993 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19