Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 233 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0353. Min Range: -5.0353
Max Act: 5.0353. Min Act: -0.1700
Data Index: 6885487 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.9728. Min Act: -0.1700
Data Index: 8457536 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8791. Min Act: -0.1700
Data Index: 4444901 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 2717586 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8478. Min Act: -0.1700
Data Index: 7310192 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7853. Min Act: -0.1700
Data Index: 5184804 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.8166. Min Act: -0.1700
Data Index: 6537613 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7228. Min Act: -0.1700
Data Index: 8690411 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7228. Min Act: -0.1700
Data Index: 763643 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6916. Min Act: -0.1700
Data Index: 14288 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6916. Min Act: -0.1700
Data Index: 4722950 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.7228. Min Act: -0.1700
Data Index: 7571926 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6916. Min Act: -0.1700
Data Index: 4454362 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6916. Min Act: -0.1700
Data Index: 3575768 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6603. Min Act: -0.1700
Data Index: 4383293 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6603. Min Act: -0.1700
Data Index: 6808549 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6603. Min Act: -0.1700
Data Index: 2396287 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6603. Min Act: -0.1700
Data Index: 7264607 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6291. Min Act: -0.1700
Data Index: 4122020 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0353. Min Range: -5.0353
Max Act: 4.6603. Min Act: -0.1700
Data Index: 2042074 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19