Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2002 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.7381. Min Act: -0.1700
Data Index: 6662189 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.7381. Min Act: -0.1700
Data Index: 1660717 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.7221. Min Act: -0.1700
Data Index: 7692122 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.7221. Min Act: -0.1700
Data Index: 1412490 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6741. Min Act: -0.1700
Data Index: 2466604 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6901. Min Act: -0.1700
Data Index: 2154772 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6901. Min Act: -0.1700
Data Index: 254376 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6420. Min Act: -0.1700
Data Index: 4996317 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6260. Min Act: -0.1700
Data Index: 104740 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6260. Min Act: -0.1700
Data Index: 8250959 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6260. Min Act: -0.1700
Data Index: 2905268 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6260. Min Act: -0.1700
Data Index: 2700300 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6260. Min Act: -0.1700
Data Index: 3859316 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.6260. Min Act: -0.1700
Data Index: 5441560 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.5938. Min Act: -0.1700
Data Index: 5347466 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.5938. Min Act: -0.1700
Data Index: 5201460 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.5938. Min Act: -0.1700
Data Index: 2584704 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.5777. Min Act: -0.1700
Data Index: 2405689 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.5777. Min Act: -0.1700
Data Index: 4462228 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7381. Min Range: -2.7381
Max Act: 2.5616. Min Act: -0.1700
Data Index: 8697901 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19