Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 438 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0276. Min Range: -8.0276
Max Act: 8.0276. Min Act: -0.1700
Data Index: 1626687 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0276. Min Range: -8.0276
Max Act: 8.0276. Min Act: -0.1700
Data Index: 2243023 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.9651. Min Act: -0.1700
Data Index: 5922211 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.9651. Min Act: -0.1700
Data Index: 4132342 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.9651. Min Act: -0.1700
Data Index: 6083989 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.9651. Min Act: -0.1700
Data Index: 2460598 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.9026. Min Act: -0.1700
Data Index: 231548 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.9026. Min Act: -0.1700
Data Index: 4032635 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.8401. Min Act: -0.1700
Data Index: 8110611 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.8401. Min Act: -0.1700
Data Index: 1626691 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.8401. Min Act: -0.1700
Data Index: 4472003 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.7776. Min Act: -0.1700
Data Index: 7088518 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.6838. Min Act: -0.1700
Data Index: 6323431 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.6838. Min Act: -0.1700
Data Index: 6775820 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.6838. Min Act: -0.1700
Data Index: 4848484 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.6526. Min Act: -0.1700
Data Index: 3921885 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.6526. Min Act: -0.1700
Data Index: 1626706 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.6213. Min Act: -0.1700
Data Index: 6697734 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.6213. Min Act: -0.1700
Data Index: 3355835 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0276. Min Range: -8.0276
Max Act: 7.6213. Min Act: -0.1700
Data Index: 1587780 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19