Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5967 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0716. Min Range: -7.0716
Max Act: 7.0716. Min Act: -0.1700
Data Index: 4951943 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.9466. Min Act: -0.1700
Data Index: 8011426 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.9778. Min Act: -0.1700
Data Index: 736393 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.9153. Min Act: -0.1700
Data Index: 5610999 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.8528. Min Act: -0.1700
Data Index: 8471883 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.7903. Min Act: -0.1700
Data Index: 1408144 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.7591. Min Act: -0.1700
Data Index: 1915346 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.7278. Min Act: -0.1700
Data Index: 2919372 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.7278. Min Act: -0.1700
Data Index: 6594470 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6966. Min Act: -0.1700
Data Index: 3008860 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6341. Min Act: -0.1700
Data Index: 3803893 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6653. Min Act: -0.1700
Data Index: 2910774 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6341. Min Act: -0.1700
Data Index: 5874845 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6341. Min Act: -0.1700
Data Index: 2420565 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6341. Min Act: -0.1700
Data Index: 1435485 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6028. Min Act: -0.1700
Data Index: 7285137 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6028. Min Act: -0.1700
Data Index: 8826156 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6028. Min Act: -0.1700
Data Index: 5660595 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6028. Min Act: -0.1700
Data Index: 2600690 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.5716. Min Act: -0.1700
Data Index: 8385350 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19