Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 294 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0925. Min Range: -8.0925
Max Act: 8.0925. Min Act: -0.1700
Data Index: 4148574 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0925. Min Range: -8.0925
Max Act: 8.0300. Min Act: -0.1700
Data Index: 810911 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.9987. Min Act: -0.1700
Data Index: 4565854 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.9987. Min Act: -0.1700
Data Index: 5574228 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.9675. Min Act: -0.1700
Data Index: 6171788 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.9362. Min Act: -0.1700
Data Index: 4090096 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.8737. Min Act: -0.1700
Data Index: 8024493 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.7800. Min Act: -0.1700
Data Index: 1280105 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.7800. Min Act: -0.1700
Data Index: 7075763 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.7487. Min Act: -0.1700
Data Index: 3884640 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.7487. Min Act: -0.1700
Data Index: 7789574 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.7487. Min Act: -0.1700
Data Index: 2452622 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.6862. Min Act: -0.1700
Data Index: 6268365 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.7175. Min Act: -0.1700
Data Index: 5177688 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.7175. Min Act: -0.1700
Data Index: 4975219 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.7175. Min Act: -0.1700
Data Index: 2881485 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.6862. Min Act: -0.1700
Data Index: 5952493 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.6550. Min Act: -0.1700
Data Index: 907299 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.6550. Min Act: -0.1700
Data Index: 5301677 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0925. Min Range: -8.0925
Max Act: 7.6237. Min Act: -0.1700
Data Index: 1266601 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19