Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5274 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1274. Min Range: -7.1274
Max Act: 7.1274. Min Act: -0.1700
Data Index: 172069 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.9712. Min Act: -0.1700
Data Index: 1315385 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6899. Min Act: -0.1700
Data Index: 5507727 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6899. Min Act: -0.1700
Data Index: 1445982 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6587. Min Act: -0.1700
Data Index: 1385362 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6274. Min Act: -0.1700
Data Index: 3086644 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5649. Min Act: -0.1700
Data Index: 4242219 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5337. Min Act: -0.1700
Data Index: 6490201 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5337. Min Act: -0.1700
Data Index: 3565002 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5337. Min Act: -0.1700
Data Index: 2478967 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5024. Min Act: -0.1700
Data Index: 518382 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.4399. Min Act: -0.1700
Data Index: 2198707 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.4399. Min Act: -0.1700
Data Index: 7899084 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.4399. Min Act: -0.1700
Data Index: 7207213 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.4087. Min Act: -0.1700
Data Index: 6140287 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.3774. Min Act: -0.1700
Data Index: 1630735 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.4087. Min Act: -0.1700
Data Index: 4586948 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.4399. Min Act: -0.1700
Data Index: 4228554 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.4087. Min Act: -0.1700
Data Index: 2183574 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.3774. Min Act: -0.1700
Data Index: 2908718 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19