Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.9615. Min Act: -0.1700
Data Index: 7368294 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.7740. Min Act: -0.1700
Data Index: 4814673 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.7740. Min Act: -0.1700
Data Index: 1082151 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.5240. Min Act: -0.1700
Data Index: 2499379 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.3990. Min Act: -0.1700
Data Index: 1495166 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.3990. Min Act: -0.1700
Data Index: 5657830 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.3365. Min Act: -0.1700
Data Index: 5172317 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.3365. Min Act: -0.1700
Data Index: 6509717 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.2740. Min Act: -0.1700
Data Index: 7911626 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.2740. Min Act: -0.1700
Data Index: 7191765 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.2740. Min Act: -0.1700
Data Index: 7344429 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.2115. Min Act: -0.1700
Data Index: 6195619 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.2115. Min Act: -0.1700
Data Index: 5052136 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.1490. Min Act: -0.1700
Data Index: 4688181 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.0865. Min Act: -0.1700
Data Index: 4346063 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.0865. Min Act: -0.1700
Data Index: 6424782 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.0865. Min Act: -0.1700
Data Index: 4224768 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.0865. Min Act: -0.1700
Data Index: 4770644 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.0865. Min Act: -0.1700
Data Index: 2606749 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9615. Min Range: -8.9615
Max Act: 8.0240. Min Act: -0.1700
Data Index: 505078 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19