Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2723 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.4327. Min Act: -0.1700
Data Index: 2705247 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.4327. Min Act: -0.1700
Data Index: 5840175 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.4640. Min Act: -0.1700
Data Index: 2280124 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3702. Min Act: -0.1700
Data Index: 2895808 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.4015. Min Act: -0.1700
Data Index: 4925707 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.4327. Min Act: -0.1700
Data Index: 7083449 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3702. Min Act: -0.1700
Data Index: 8099124 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3390. Min Act: -0.1700
Data Index: 1987115 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3390. Min Act: -0.1700
Data Index: 8510893 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3390. Min Act: -0.1700
Data Index: 4683394 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3390. Min Act: -0.1700
Data Index: 1327563 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3390. Min Act: -0.1700
Data Index: 6479544 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3077. Min Act: -0.1699
Data Index: 581945 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3077. Min Act: -0.1700
Data Index: 6742377 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.3077. Min Act: -0.1700
Data Index: 249560 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.2765. Min Act: -0.1700
Data Index: 581886 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.2765. Min Act: -0.1700
Data Index: 6972430 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.2765. Min Act: -0.1700
Data Index: 7813152 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.2765. Min Act: -0.1700
Data Index: 8495121 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4640. Min Range: -5.4640
Max Act: 5.2452. Min Act: -0.1700
Data Index: 5861508 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19