Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.8765. Min Act: -0.1700
Data Index: 7188253 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.6890. Min Act: -0.1700
Data Index: 1008891 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.5640. Min Act: -0.1700
Data Index: 181193 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.5640. Min Act: -0.1700
Data Index: 3253058 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.5327. Min Act: -0.1700
Data Index: 3376078 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.5327. Min Act: -0.1700
Data Index: 7767658 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.5015. Min Act: -0.1700
Data Index: 966145 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4702. Min Act: -0.1700
Data Index: 4998769 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.5015. Min Act: -0.1700
Data Index: 8267555 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.5015. Min Act: -0.1700
Data Index: 3789618 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.5015. Min Act: -0.1700
Data Index: 1325645 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4702. Min Act: -0.1700
Data Index: 13807 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4702. Min Act: -0.1700
Data Index: 2888470 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4702. Min Act: -0.1700
Data Index: 5334715 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4702. Min Act: -0.1700
Data Index: 1360396 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4390. Min Act: -0.1700
Data Index: 5044283 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4077. Min Act: -0.1700
Data Index: 1529658 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4077. Min Act: -0.1700
Data Index: 563107 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4390. Min Act: -0.1700
Data Index: 2109801 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8765. Min Range: -6.8765
Max Act: 6.4077. Min Act: -0.1700
Data Index: 2869610 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19