Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5198 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.3604. Min Act: -0.1700
Data Index: 1098227 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.3292. Min Act: -0.1700
Data Index: 3267800 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.2667. Min Act: -0.1700
Data Index: 7971202 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.2354. Min Act: -0.1700
Data Index: 1187227 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.2042. Min Act: -0.1700
Data Index: 7857986 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.1729. Min Act: -0.1700
Data Index: 3804056 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.1729. Min Act: -0.1700
Data Index: 5531178 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.1104. Min Act: -0.1700
Data Index: 2982362 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.1104. Min Act: -0.1700
Data Index: 3648467 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.1104. Min Act: -0.1700
Data Index: 2785344 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.0479. Min Act: -0.1700
Data Index: 7072033 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.0479. Min Act: -0.1700
Data Index: 915154 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.0167. Min Act: -0.1700
Data Index: 7462167 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.0167. Min Act: -0.1700
Data Index: 5016378 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3604. Min Range: -6.3604
Max Act: 6.0167. Min Act: -0.1700
Data Index: 7805770 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.9542. Min Act: -0.1700
Data Index: 6438002 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.9854. Min Act: -0.1700
Data Index: 1691459 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.9542. Min Act: -0.1700
Data Index: 1293634 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.9542. Min Act: -0.1700
Data Index: 4940876 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3604. Min Range: -6.3604
Max Act: 5.9542. Min Act: -0.1700
Data Index: 3648468 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19