Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2533. Min Range: -6.2533
Max Act: 6.2533. Min Act: -0.1700
Data Index: 2544363 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2533. Min Range: -6.2533
Max Act: 6.1908. Min Act: -0.1700
Data Index: 6714547 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2533. Min Range: -6.2533
Max Act: 6.0658. Min Act: -0.1700
Data Index: 1279090 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.9720. Min Act: -0.1700
Data Index: 3203226 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.8783. Min Act: -0.1700
Data Index: 202939 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.8783. Min Act: -0.1700
Data Index: 2923581 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.6283. Min Act: -0.1700
Data Index: 4071589 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.5658. Min Act: -0.1700
Data Index: 7291474 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.5658. Min Act: -0.1700
Data Index: 4099829 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.5345. Min Act: -0.1700
Data Index: 2382504 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.5345. Min Act: -0.1700
Data Index: 2340963 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.5658. Min Act: -0.1700
Data Index: 868013 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.5345. Min Act: -0.1700
Data Index: 1937185 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.4408. Min Act: -0.1700
Data Index: 5890021 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.4408. Min Act: -0.1700
Data Index: 4937448 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.3783. Min Act: -0.1700
Data Index: 8636199 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.4095. Min Act: -0.1700
Data Index: 1944618 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.4095. Min Act: -0.1700
Data Index: 4560113 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.3783. Min Act: -0.1700
Data Index: 6144541 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2533. Min Range: -6.2533
Max Act: 5.3783. Min Act: -0.1700
Data Index: 1831337 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19