Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1522 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.6898. Min Act: -0.1700
Data Index: 882199 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.7054. Min Act: -0.1700
Data Index: 7388331 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.6272. Min Act: -0.1700
Data Index: 2619002 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.5959. Min Act: -0.1700
Data Index: 402555 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.5803. Min Act: -0.1700
Data Index: 5995247 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.5646. Min Act: -0.1700
Data Index: 4136156 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.5489. Min Act: -0.1700
Data Index: 5268700 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.5489. Min Act: -0.1700
Data Index: 8130190 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.5333. Min Act: -0.1700
Data Index: 278561 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.5020. Min Act: -0.1700
Data Index: 1923302 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4863. Min Act: -0.1700
Data Index: 2277474 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4706. Min Act: -0.1700
Data Index: 1699072 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4393. Min Act: -0.1700
Data Index: 5221335 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4393. Min Act: -0.1700
Data Index: 1987771 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4236. Min Act: -0.1700
Data Index: 3115378 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4236. Min Act: -0.1700
Data Index: 5189882 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4236. Min Act: -0.1700
Data Index: 2132228 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4393. Min Act: -0.1700
Data Index: 1430853 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4236. Min Act: -0.1700
Data Index: 500780 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7054. Min Range: -3.7054
Max Act: 3.4080. Min Act: -0.1700
Data Index: 7710771 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19