Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2056 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.6692. Min Act: -0.1700
Data Index: 6870569 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.6692. Min Act: -0.1700
Data Index: 1853355 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.6380. Min Act: -0.1700
Data Index: 2363154 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.5755. Min Act: -0.1700
Data Index: 7067937 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.5130. Min Act: -0.1700
Data Index: 4550645 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.5130. Min Act: -0.1700
Data Index: 6821813 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4817. Min Act: -0.1700
Data Index: 3119333 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4505. Min Act: -0.1700
Data Index: 3491419 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4505. Min Act: -0.1700
Data Index: 5229120 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4817. Min Act: -0.1700
Data Index: 2190282 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4192. Min Act: -0.1700
Data Index: 1328784 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.4192. Min Act: -0.1700
Data Index: 4080985 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.3880. Min Act: -0.1700
Data Index: 660971 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.3880. Min Act: -0.1700
Data Index: 1813003 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.3880. Min Act: -0.1700
Data Index: 7063384 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.3567. Min Act: -0.1700
Data Index: 4378076 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.3567. Min Act: -0.1700
Data Index: 4007372 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.3567. Min Act: -0.1700
Data Index: 2019492 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.3567. Min Act: -0.1700
Data Index: 6764281 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6692. Min Range: -5.6692
Max Act: 5.3255. Min Act: -0.1700
Data Index: 3425823 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19