Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2337. Min Range: -2.2337
Max Act: 2.2337. Min Act: -0.1700
Data Index: 2461897 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2337. Min Range: -2.2337
Max Act: 2.0587. Min Act: -0.1700
Data Index: 4182639 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2337. Min Range: -2.2337
Max Act: 2.0587. Min Act: -0.1700
Data Index: 3209861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2337. Min Range: -2.2337
Max Act: 2.0418. Min Act: -0.1700
Data Index: 4682819 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.9912. Min Act: -0.1700
Data Index: 3656590 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.9403. Min Act: -0.1700
Data Index: 323538 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.9403. Min Act: -0.1700
Data Index: 2874633 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.9403. Min Act: -0.1700
Data Index: 4004083 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.9233. Min Act: -0.1700
Data Index: 3684074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.9063. Min Act: -0.1700
Data Index: 1935444 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.9148. Min Act: -0.1700
Data Index: 7483741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.9148. Min Act: -0.1699
Data Index: 1239259 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.9148. Min Act: -0.1699
Data Index: 5101094 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.8978. Min Act: -0.1700
Data Index: 7086846 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.8893. Min Act: -0.1697
Data Index: 2412057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.8893. Min Act: -0.1700
Data Index: 1610482 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.8807. Min Act: -0.1700
Data Index: 3604777 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.8636. Min Act: -0.1700
Data Index: 5425932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.8636. Min Act: -0.1700
Data Index: 8159140 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2337. Min Range: -2.2337
Max Act: 1.8636. Min Act: -0.1700
Data Index: 5725238 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19