Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.4778. Min Act: -0.1700
Data Index: 8574650 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.4153. Min Act: -0.1700
Data Index: 7165221 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.3528. Min Act: -0.1700
Data Index: 5175326 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.2903. Min Act: -0.1700
Data Index: 1510386 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.1653. Min Act: -0.1700
Data Index: 864316 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.1340. Min Act: -0.1700
Data Index: 5356265 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.1028. Min Act: -0.1700
Data Index: 6810802 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.0715. Min Act: -0.1700
Data Index: 7461770 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.0403. Min Act: -0.1700
Data Index: 4196160 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4778. Min Range: -5.4778
Max Act: 5.0090. Min Act: -0.1700
Data Index: 5462159 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.9778. Min Act: -0.1700
Data Index: 1580944 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.9778. Min Act: -0.1700
Data Index: 2172861 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.9465. Min Act: -0.1700
Data Index: 2047169 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.9465. Min Act: -0.1700
Data Index: 2819477 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.9465. Min Act: -0.1700
Data Index: 6005625 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.9465. Min Act: -0.1700
Data Index: 7468418 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.9153. Min Act: -0.1700
Data Index: 5845929 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.8840. Min Act: -0.1700
Data Index: 7401865 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.8840. Min Act: -0.1700
Data Index: 3191813 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4778. Min Range: -5.4778
Max Act: 4.8840. Min Act: -0.1700
Data Index: 722496 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19