Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.3542. Min Act: -0.1700
Data Index: 6317104 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2721. Min Act: -0.1700
Data Index: 6945577 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2721. Min Act: -0.1700
Data Index: 6501523 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2390. Min Act: -0.1700
Data Index: 3725906 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2225. Min Act: -0.1700
Data Index: 1328762 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2556. Min Act: -0.1700
Data Index: 6748320 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2390. Min Act: -0.1700
Data Index: 5381783 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2390. Min Act: -0.1700
Data Index: 3417143 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2225. Min Act: -0.1700
Data Index: 8638814 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2225. Min Act: -0.1700
Data Index: 6438947 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2059. Min Act: -0.1700
Data Index: 7488681 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2059. Min Act: -0.1700
Data Index: 216864 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2059. Min Act: -0.1700
Data Index: 4595450 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2059. Min Act: -0.1700
Data Index: 2594846 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2059. Min Act: -0.1700
Data Index: 5992446 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2059. Min Act: -0.1700
Data Index: 7498587 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2059. Min Act: -0.1700
Data Index: 5648692 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.2059. Min Act: -0.1700
Data Index: 7392100 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.1893. Min Act: -0.1700
Data Index: 2046285 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3542. Min Range: -2.3542
Max Act: 2.1727. Min Act: -0.1700
Data Index: 1179865 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19