Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2513 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.7615. Min Act: -0.1700
Data Index: 1613499 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 7069766 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 79775 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 622279 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 6651984 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 7808382 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6990. Min Act: -0.1700
Data Index: 7439339 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 1924766 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 7679563 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 6067671 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 4544216 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 3943370 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 4601213 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 4389446 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 3165456 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 6978174 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 2955397 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 7565586 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 2602232 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7615. Min Range: -4.7615
Max Act: 4.6678. Min Act: -0.1700
Data Index: 5248454 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19