Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3552 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0078. Min Range: -3.0078
Max Act: 3.0078. Min Act: -0.1700
Data Index: 7140718 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.9445. Min Act: -0.1700
Data Index: 3530504 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.9287. Min Act: -0.1700
Data Index: 1071349 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.9287. Min Act: -0.1700
Data Index: 3820738 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.9129. Min Act: -0.1700
Data Index: 4932731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8970. Min Act: -0.1700
Data Index: 7638507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8811. Min Act: -0.1700
Data Index: 1247992 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8811. Min Act: -0.1700
Data Index: 5259695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8811. Min Act: -0.1700
Data Index: 3822655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8811. Min Act: -0.1700
Data Index: 2094275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8653. Min Act: -0.1700
Data Index: 1390356 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8494. Min Act: -0.1700
Data Index: 8095137 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8335. Min Act: -0.1700
Data Index: 6518741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8335. Min Act: -0.1700
Data Index: 4872761 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8335. Min Act: -0.1700
Data Index: 4584744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8335. Min Act: -0.1700
Data Index: 722322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8335. Min Act: -0.1700
Data Index: 2620425 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8335. Min Act: -0.1700
Data Index: 7454487 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8335. Min Act: -0.1700
Data Index: 4297860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0078. Min Range: -3.0078
Max Act: 2.8176. Min Act: -0.1700
Data Index: 4027985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19