Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2341. Min Range: -7.2341
Max Act: 7.2341. Min Act: -0.1700
Data Index: 7082933 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2341. Min Range: -7.2341
Max Act: 7.0466. Min Act: -0.1700
Data Index: 6995702 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2341. Min Range: -7.2341
Max Act: 7.0153. Min Act: -0.1700
Data Index: 7908440 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.9528. Min Act: -0.1700
Data Index: 1828769 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.9841. Min Act: -0.1700
Data Index: 5196382 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.9216. Min Act: -0.1700
Data Index: 6998003 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.8903. Min Act: -0.1700
Data Index: 1908005 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.8591. Min Act: -0.1700
Data Index: 6885393 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.7966. Min Act: -0.1700
Data Index: 3108418 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.7653. Min Act: -0.1700
Data Index: 1148269 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.6716. Min Act: -0.1700
Data Index: 1391123 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.6716. Min Act: -0.1700
Data Index: 162714 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.6403. Min Act: -0.1700
Data Index: 2613233 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.6403. Min Act: -0.1700
Data Index: 8252555 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.6403. Min Act: -0.1700
Data Index: 1566896 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.6091. Min Act: -0.1700
Data Index: 4923221 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.6091. Min Act: -0.1700
Data Index: 6056575 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.5778. Min Act: -0.1700
Data Index: 541113 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.5778. Min Act: -0.1700
Data Index: 5250392 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2341. Min Range: -7.2341
Max Act: 6.5778. Min Act: -0.1700
Data Index: 506425 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19