Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5345 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.8312. Min Act: -0.1700
Data Index: 5839247 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.7374. Min Act: -0.1700
Data Index: 3955488 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.6749. Min Act: -0.1700
Data Index: 419704 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.6437. Min Act: -0.1700
Data Index: 5929063 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.6124. Min Act: -0.1700
Data Index: 8625123 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.5812. Min Act: -0.1700
Data Index: 5990119 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.5499. Min Act: -0.1700
Data Index: 78642 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.5499. Min Act: -0.1700
Data Index: 2336845 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.5187. Min Act: -0.1700
Data Index: 6542639 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.5187. Min Act: -0.1699
Data Index: 1545085 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4874. Min Act: -0.1699
Data Index: 8241184 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4874. Min Act: -0.1697
Data Index: 8474655 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4874. Min Act: -0.1700
Data Index: 4244530 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4874. Min Act: -0.1700
Data Index: 8745403 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4562. Min Act: -0.1700
Data Index: 4141931 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4562. Min Act: -0.1700
Data Index: 4126353 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4562. Min Act: -0.1700
Data Index: 2805429 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4562. Min Act: -0.1700
Data Index: 5584266 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4249. Min Act: -0.1700
Data Index: 5976566 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8312. Min Range: -5.8312
Max Act: 5.4249. Min Act: -0.1700
Data Index: 2270984 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19