Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1203 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.4249. Min Act: -0.1700
Data Index: 7419311 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.3311. Min Act: -0.1700
Data Index: 2446623 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.2999. Min Act: -0.1700
Data Index: 7299900 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.2999. Min Act: -0.1700
Data Index: 2416813 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.2999. Min Act: -0.1700
Data Index: 8429710 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.2686. Min Act: -0.1700
Data Index: 6844223 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.2374. Min Act: -0.1700
Data Index: 606948 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.2374. Min Act: -0.1700
Data Index: 4502481 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.2061. Min Act: -0.1700
Data Index: 6117480 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.1749. Min Act: -0.1700
Data Index: 6180421 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.1749. Min Act: -0.1700
Data Index: 3638880 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.1436. Min Act: -0.1700
Data Index: 3379413 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.1436. Min Act: -0.1700
Data Index: 885985 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.1124. Min Act: -0.1700
Data Index: 3623857 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.1124. Min Act: -0.1700
Data Index: 6554943 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.1124. Min Act: -0.1700
Data Index: 3108130 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.0811. Min Act: -0.1700
Data Index: 5557881 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.0811. Min Act: -0.1700
Data Index: 4287394 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.0811. Min Act: -0.1700
Data Index: 2584604 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4249. Min Range: -6.4249
Max Act: 6.0499. Min Act: -0.1700
Data Index: 4497643 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19