Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.8455. Min Act: -0.1700
Data Index: 2648193 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.8455. Min Act: -0.1699
Data Index: 714567 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.8201. Min Act: -0.1691
Data Index: 3055232 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.8286. Min Act: -0.1676
Data Index: 3263590 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.8201. Min Act: -0.1664
Data Index: 2953641 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.8117. Min Act: -0.1700
Data Index: 1840397 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.8117. Min Act: -0.1700
Data Index: 2989594 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7782. Min Act: -0.1689
Data Index: 3290561 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7782. Min Act: -0.1690
Data Index: 3521456 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7699. Min Act: -0.1697
Data Index: 2038383 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7616. Min Act: -0.1700
Data Index: 3343764 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7533. Min Act: -0.1700
Data Index: 437912 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7450. Min Act: -0.1699
Data Index: 8375841 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7367. Min Act: -0.1698
Data Index: 516961 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7285. Min Act: -0.1700
Data Index: 6719802 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7203. Min Act: -0.1699
Data Index: 3933467 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7121. Min Act: -0.1700
Data Index: 3507866 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7203. Min Act: -0.1698
Data Index: 7515285 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7203. Min Act: -0.1700
Data Index: 6826181 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8455. Min Range: -0.8455
Max Act: 0.7121. Min Act: -0.1690
Data Index: 8635109 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19