Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4655 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.8615. Min Act: -0.1700
Data Index: 2540729 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.6427. Min Act: -0.1700
Data Index: 1808355 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.6115. Min Act: -0.1700
Data Index: 7558392 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.6115. Min Act: -0.1700
Data Index: 6752612 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.5177. Min Act: -0.1700
Data Index: 3827100 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4865. Min Act: -0.1700
Data Index: 3234127 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4865. Min Act: -0.1700
Data Index: 3470399 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4865. Min Act: -0.1700
Data Index: 4805633 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4552. Min Act: -0.1700
Data Index: 4813818 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4240. Min Act: -0.1700
Data Index: 3687202 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4240. Min Act: -0.1700
Data Index: 6258079 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4240. Min Act: -0.1700
Data Index: 1808353 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4240. Min Act: -0.1700
Data Index: 1688105 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.4240. Min Act: -0.1700
Data Index: 8806172 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.3927. Min Act: -0.1700
Data Index: 3280727 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.3927. Min Act: -0.1700
Data Index: 4813817 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.3927. Min Act: -0.1700
Data Index: 4147215 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.3615. Min Act: -0.1700
Data Index: 3161451 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.3615. Min Act: -0.1700
Data Index: 3915876 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8615. Min Range: -5.8615
Max Act: 5.3615. Min Act: -0.1700
Data Index: 6164776 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19