Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2542 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.8032. Min Act: -0.1700
Data Index: 21216 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.7094. Min Act: -0.1689
Data Index: 4559679 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.6469. Min Act: -0.1700
Data Index: 4623261 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.6157. Min Act: -0.1700
Data Index: 6140007 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.6157. Min Act: -0.1700
Data Index: 4657301 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.6157. Min Act: -0.1700
Data Index: 3950837 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.5219. Min Act: -0.1699
Data Index: 1949892 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.4907. Min Act: -0.1697
Data Index: 6859619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.4907. Min Act: -0.1698
Data Index: 1810105 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.4594. Min Act: -0.1686
Data Index: 1586522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.4594. Min Act: -0.1700
Data Index: 4469323 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.4282. Min Act: -0.1700
Data Index: 5416410 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.3969. Min Act: -0.1699
Data Index: 8225116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.3657. Min Act: -0.1699
Data Index: 5335253 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.3657. Min Act: -0.1700
Data Index: 7921209 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.3657. Min Act: -0.1681
Data Index: 1359251 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.3344. Min Act: -0.1699
Data Index: 6358620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.3344. Min Act: -0.1700
Data Index: 3886741 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.3344. Min Act: -0.1700
Data Index: 512 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8032. Min Range: -5.8032
Max Act: 5.3344. Min Act: -0.1699
Data Index: 606210 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19