Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2670 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.2514. Min Act: -0.1700
Data Index: 1773430 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.2514. Min Act: -0.1700
Data Index: 2639571 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.2514. Min Act: -0.1700
Data Index: 122022 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.2201. Min Act: -0.1700
Data Index: 122021 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.2201. Min Act: -0.1700
Data Index: 5694095 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1889. Min Act: -0.1700
Data Index: 8090873 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1889. Min Act: -0.1700
Data Index: 3838875 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1576. Min Act: -0.1700
Data Index: 6718880 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1576. Min Act: -0.1700
Data Index: 5840494 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1576. Min Act: -0.1700
Data Index: 5484335 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1264. Min Act: -0.1700
Data Index: 2316753 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1264. Min Act: -0.1700
Data Index: 5846033 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1264. Min Act: -0.1700
Data Index: 2569318 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1264. Min Act: -0.1700
Data Index: 8541942 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1264. Min Act: -0.1700
Data Index: 5181476 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1264. Min Act: -0.1700
Data Index: 7880629 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1264. Min Act: -0.1700
Data Index: 6864403 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.1576. Min Act: -0.1700
Data Index: 2960541 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.0951. Min Act: -0.1700
Data Index: 2737374 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2514. Min Range: -4.2514
Max Act: 4.0951. Min Act: -0.1700
Data Index: 168323 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19