Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3593 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0283. Min Range: -8.0283
Max Act: 8.0283. Min Act: -0.1700
Data Index: 8149071 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.9658. Min Act: -0.1700
Data Index: 6974400 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.9033. Min Act: -0.1700
Data Index: 2454244 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.8408. Min Act: -0.1700
Data Index: 5765908 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.8408. Min Act: -0.1700
Data Index: 6688576 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.7158. Min Act: -0.1700
Data Index: 1656857 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.6845. Min Act: -0.1700
Data Index: 4781393 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.6845. Min Act: -0.1700
Data Index: 2513120 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.6845. Min Act: -0.1700
Data Index: 5259162 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.6533. Min Act: -0.1700
Data Index: 8132949 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.6845. Min Act: -0.1700
Data Index: 4723407 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.6845. Min Act: -0.1700
Data Index: 3071248 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.6220. Min Act: -0.1700
Data Index: 8516331 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.6220. Min Act: -0.1700
Data Index: 6171243 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.5908. Min Act: -0.1700
Data Index: 6723841 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.5283. Min Act: -0.1700
Data Index: 898274 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.5595. Min Act: -0.1700
Data Index: 8529833 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.5283. Min Act: -0.1700
Data Index: 755252 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.4970. Min Act: -0.1700
Data Index: 2257781 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0283. Min Range: -8.0283
Max Act: 7.4970. Min Act: -0.1700
Data Index: 4449711 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19