Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4216 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.3481. Min Act: -0.1700
Data Index: 1038266 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.2231. Min Act: -0.1700
Data Index: 5575970 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.1918. Min Act: -0.1700
Data Index: 1695261 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.0980. Min Act: -0.1700
Data Index: 1198641 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.0980. Min Act: -0.1700
Data Index: 8251672 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.1293. Min Act: -0.1700
Data Index: 8206428 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.0355. Min Act: -0.1700
Data Index: 4858452 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.0355. Min Act: -0.1700
Data Index: 3346592 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.0355. Min Act: -0.1700
Data Index: 1381914 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.0355. Min Act: -0.1700
Data Index: 3799562 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.0043. Min Act: -0.1700
Data Index: 8187061 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.0043. Min Act: -0.1700
Data Index: 7165422 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3481. Min Range: -4.3481
Max Act: 4.0043. Min Act: -0.1700
Data Index: 6928499 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3481. Min Range: -4.3481
Max Act: 3.9730. Min Act: -0.1700
Data Index: 4933863 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3481. Min Range: -4.3481
Max Act: 3.9730. Min Act: -0.1700
Data Index: 1206813 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3481. Min Range: -4.3481
Max Act: 3.9730. Min Act: -0.1700
Data Index: 886267 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3481. Min Range: -4.3481
Max Act: 3.9730. Min Act: -0.1700
Data Index: 3061003 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3481. Min Range: -4.3481
Max Act: 3.9417. Min Act: -0.1700
Data Index: 5823337 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3481. Min Range: -4.3481
Max Act: 3.9417. Min Act: -0.1700
Data Index: 8293015 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3481. Min Range: -4.3481
Max Act: 3.9417. Min Act: -0.1700
Data Index: 8780253 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19