Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2390 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1514. Min Range: -7.1514
Max Act: 7.1514. Min Act: -0.1700
Data Index: 5728078 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.9952. Min Act: -0.1700
Data Index: 2640656 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.8389. Min Act: -0.1700
Data Index: 3173902 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.6827. Min Act: -0.1700
Data Index: 692848 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.5889. Min Act: -0.1700
Data Index: 2089062 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.5577. Min Act: -0.1700
Data Index: 1161617 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.5577. Min Act: -0.1700
Data Index: 370000 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.5577. Min Act: -0.1700
Data Index: 8657118 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4952. Min Act: -0.1700
Data Index: 2089060 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4952. Min Act: -0.1700
Data Index: 6690542 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4639. Min Act: -0.1700
Data Index: 3461811 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4639. Min Act: -0.1700
Data Index: 8632416 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4639. Min Act: -0.1700
Data Index: 8784076 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4327. Min Act: -0.1700
Data Index: 4931305 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4639. Min Act: -0.1700
Data Index: 6788839 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4327. Min Act: -0.1700
Data Index: 5541684 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4327. Min Act: -0.1700
Data Index: 2317553 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4327. Min Act: -0.1700
Data Index: 3761673 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4014. Min Act: -0.1700
Data Index: 482122 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1514. Min Range: -7.1514
Max Act: 6.4014. Min Act: -0.1700
Data Index: 310210 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19