Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3382. Min Range: -8.3382
Max Act: 8.3382. Min Act: -0.1700
Data Index: 8012213 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.9007. Min Act: -0.1700
Data Index: 6970246 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.9632. Min Act: -0.1700
Data Index: 4410973 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.8382. Min Act: -0.1700
Data Index: 414848 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.7757. Min Act: -0.1700
Data Index: 7395859 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.6820. Min Act: -0.1700
Data Index: 604046 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.6507. Min Act: -0.1700
Data Index: 6305458 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.7132. Min Act: -0.1700
Data Index: 1981136 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.6507. Min Act: -0.1700
Data Index: 4876677 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.6507. Min Act: -0.1700
Data Index: 4356600 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.5882. Min Act: -0.1700
Data Index: 4322996 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.5882. Min Act: -0.1700
Data Index: 1782963 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.5570. Min Act: -0.1700
Data Index: 5774266 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.5570. Min Act: -0.1700
Data Index: 4453976 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.5570. Min Act: -0.1700
Data Index: 937780 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.5570. Min Act: -0.1700
Data Index: 8069121 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.4945. Min Act: -0.1700
Data Index: 300954 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.5257. Min Act: -0.1700
Data Index: 861487 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.4945. Min Act: -0.1700
Data Index: 2453239 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3382. Min Range: -8.3382
Max Act: 7.4945. Min Act: -0.1700
Data Index: 4526390 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19