Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 537 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4952. Min Range: -9.4952
Max Act: 9.4952. Min Act: -0.1699
Data Index: 8037616 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4952. Min Range: -9.4952
Max Act: 9.3702. Min Act: -0.1700
Data Index: 705269 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4952. Min Range: -9.4952
Max Act: 9.3702. Min Act: -0.1700
Data Index: 2346798 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4952. Min Range: -9.4952
Max Act: 9.3077. Min Act: -0.1700
Data Index: 2355896 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4952. Min Range: -9.4952
Max Act: 9.3077. Min Act: -0.1700
Data Index: 8020986 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4952. Min Range: -9.4952
Max Act: 9.2452. Min Act: -0.1700
Data Index: 8308848 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4952. Min Range: -9.4952
Max Act: 9.1827. Min Act: -0.1700
Data Index: 3409064 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.9952. Min Act: -0.1700
Data Index: 6772285 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4952. Min Range: -9.4952
Max Act: 9.0577. Min Act: -0.1700
Data Index: 5906675 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.9952. Min Act: -0.1700
Data Index: 5483093 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.9327. Min Act: -0.1700
Data Index: 1609840 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.8702. Min Act: -0.1700
Data Index: 2949670 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.8702. Min Act: -0.1700
Data Index: 4439744 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.8702. Min Act: -0.1699
Data Index: 3819002 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.7452. Min Act: -0.1700
Data Index: 4838391 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.7452. Min Act: -0.1700
Data Index: 6128038 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.6202. Min Act: -0.1700
Data Index: 3939244 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.6827. Min Act: -0.1700
Data Index: 6628478 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.6827. Min Act: -0.1700
Data Index: 8563226 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4952. Min Range: -9.4952
Max Act: 8.6827. Min Act: -0.1700
Data Index: 7960276 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19