Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0824. Min Range: -3.0824
Max Act: 3.0666. Min Act: -0.1700
Data Index: 2454005 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0824. Min Range: -3.0824
Max Act: 3.0824. Min Act: -0.1700
Data Index: 6201948 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0824. Min Range: -3.0824
Max Act: 3.0035. Min Act: -0.1700
Data Index: 5699197 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0824. Min Range: -3.0824
Max Act: 3.0035. Min Act: -0.1700
Data Index: 2332583 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.9718. Min Act: -0.1700
Data Index: 1919655 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.9560. Min Act: -0.1700
Data Index: 4741020 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.9402. Min Act: -0.1700
Data Index: 4721074 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.9243. Min Act: -0.1700
Data Index: 4757655 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.9085. Min Act: -0.1700
Data Index: 4366038 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.9085. Min Act: -0.1700
Data Index: 8121764 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.9085. Min Act: -0.1700
Data Index: 5105285 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.8926. Min Act: -0.1700
Data Index: 4366018 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.8926. Min Act: -0.1700
Data Index: 7695385 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.8926. Min Act: -0.1700
Data Index: 8670111 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.8609. Min Act: -0.1700
Data Index: 1916514 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.8450. Min Act: -0.1700
Data Index: 1984558 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.8450. Min Act: -0.1700
Data Index: 8568085 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.8609. Min Act: -0.1700
Data Index: 4882247 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.8450. Min Act: -0.1700
Data Index: 3223051 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0824. Min Range: -3.0824
Max Act: 2.8132. Min Act: -0.1700
Data Index: 2553234 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19