Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.4858. Min Act: -0.1700
Data Index: 3481205 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.3295. Min Act: -0.1700
Data Index: 1386515 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.3295. Min Act: -0.1700
Data Index: 1702915 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.2358. Min Act: -0.1700
Data Index: 5730305 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.1733. Min Act: -0.1700
Data Index: 6355189 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.1733. Min Act: -0.1700
Data Index: 309181 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.1733. Min Act: -0.1700
Data Index: 1841404 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.1420. Min Act: -0.1700
Data Index: 5160324 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.1420. Min Act: -0.1700
Data Index: 1438121 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.1420. Min Act: -0.1700
Data Index: 866906 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.0795. Min Act: -0.1700
Data Index: 6505929 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.1108. Min Act: -0.1700
Data Index: 7994321 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.0795. Min Act: -0.1700
Data Index: 5837536 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.0795. Min Act: -0.1700
Data Index: 6987116 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.0795. Min Act: -0.1700
Data Index: 7034044 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.1108. Min Act: -0.1700
Data Index: 5684216 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.0795. Min Act: -0.1700
Data Index: 3421588 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.0483. Min Act: -0.1700
Data Index: 2082023 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.0483. Min Act: -0.1700
Data Index: 5597349 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4858. Min Range: -5.4858
Max Act: 5.0483. Min Act: -0.1700
Data Index: 7473115 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19