Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4490 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.7263. Min Act: -0.1700
Data Index: 1441105 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.6324. Min Act: -0.1700
Data Index: 7542247 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.5855. Min Act: -0.1700
Data Index: 8328305 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.5541. Min Act: -0.1700
Data Index: 4095362 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.5385. Min Act: -0.1700
Data Index: 6992932 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.5228. Min Act: -0.1700
Data Index: 5742945 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.5072. Min Act: -0.1700
Data Index: 2443664 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.5072. Min Act: -0.1700
Data Index: 3856219 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4758. Min Act: -0.1700
Data Index: 6195887 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4915. Min Act: -0.1700
Data Index: 3877344 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4915. Min Act: -0.1700
Data Index: 5624726 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4915. Min Act: -0.1700
Data Index: 6014201 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4758. Min Act: -0.1700
Data Index: 4590185 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4915. Min Act: -0.1700
Data Index: 125435 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4915. Min Act: -0.1700
Data Index: 4843080 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4758. Min Act: -0.1700
Data Index: 6414727 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4602. Min Act: -0.1700
Data Index: 4206254 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4602. Min Act: -0.1700
Data Index: 4077473 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4288. Min Act: -0.1700
Data Index: 1358279 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7263. Min Range: -3.7263
Max Act: 3.4602. Min Act: -0.1700
Data Index: 5894 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19