Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1379 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.8328. Min Act: -0.1700
Data Index: 4748397 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.7703. Min Act: -0.1700
Data Index: 5259695 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.4578. Min Act: -0.1700
Data Index: 6358021 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.3953. Min Act: -0.1700
Data Index: 6496981 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.3953. Min Act: -0.1700
Data Index: 6129337 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.3328. Min Act: -0.1700
Data Index: 6934831 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.2703. Min Act: -0.1700
Data Index: 6129329 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.2078. Min Act: -0.1700
Data Index: 6129336 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.2703. Min Act: -0.1700
Data Index: 6270160 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.2703. Min Act: -0.1700
Data Index: 6129327 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.2078. Min Act: -0.1700
Data Index: 7766747 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.2078. Min Act: -0.1700
Data Index: 6270161 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.2078. Min Act: -0.1700
Data Index: 623349 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.1453. Min Act: -0.1700
Data Index: 1049615 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.1141. Min Act: -0.1700
Data Index: 2396752 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.0828. Min Act: -0.1700
Data Index: 7471787 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.1453. Min Act: -0.1700
Data Index: 6164632 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.0203. Min Act: -0.1700
Data Index: 1163343 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8328. Min Range: -8.8328
Max Act: 8.0203. Min Act: -0.1700
Data Index: 8737511 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8328. Min Range: -8.8328
Max Act: 7.9578. Min Act: -0.1700
Data Index: 6129328 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19