Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5575 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.5615. Min Act: -0.1700
Data Index: 4809221 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.3115. Min Act: -0.1700
Data Index: 6424265 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2802. Min Act: -0.1700
Data Index: 1684568 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2490. Min Act: -0.1700
Data Index: 7938570 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2490. Min Act: -0.1700
Data Index: 4096461 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1865. Min Act: -0.1700
Data Index: 6028552 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2177. Min Act: -0.1700
Data Index: 1551083 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.2177. Min Act: -0.1700
Data Index: 7523708 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1865. Min Act: -0.1700
Data Index: 8554352 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1865. Min Act: -0.1700
Data Index: 1262521 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1865. Min Act: -0.1700
Data Index: 3930218 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1552. Min Act: -0.1700
Data Index: 6468708 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1552. Min Act: -0.1700
Data Index: 2709100 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1552. Min Act: -0.1700
Data Index: 6509888 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1552. Min Act: -0.1700
Data Index: 5652928 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1240. Min Act: -0.1700
Data Index: 6708655 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1240. Min Act: -0.1700
Data Index: 864773 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.1240. Min Act: -0.1700
Data Index: 370331 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.0927. Min Act: -0.1700
Data Index: 4455170 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5615. Min Range: -5.5615
Max Act: 5.0927. Min Act: -0.1700
Data Index: 3007043 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19