Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.3522. Min Act: -0.1700
Data Index: 6649663 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.1960. Min Act: -0.1700
Data Index: 4226750 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.1960. Min Act: -0.1700
Data Index: 21504 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.1647. Min Act: -0.1700
Data Index: 79402 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.1647. Min Act: -0.1700
Data Index: 3175076 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.1022. Min Act: -0.1700
Data Index: 4382815 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.1022. Min Act: -0.1700
Data Index: 1098547 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.1022. Min Act: -0.1700
Data Index: 8280082 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.0710. Min Act: -0.1700
Data Index: 8796185 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.0397. Min Act: -0.1700
Data Index: 5892574 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.0397. Min Act: -0.1700
Data Index: 3455751 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.0085. Min Act: -0.1700
Data Index: 4063407 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3522. Min Range: -5.3522
Max Act: 4.9772. Min Act: -0.1700
Data Index: 2494298 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3522. Min Range: -5.3522
Max Act: 5.0085. Min Act: -0.1700
Data Index: 1619859 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3522. Min Range: -5.3522
Max Act: 4.9772. Min Act: -0.1700
Data Index: 1842485 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3522. Min Range: -5.3522
Max Act: 4.9460. Min Act: -0.1700
Data Index: 7423489 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3522. Min Range: -5.3522
Max Act: 4.9460. Min Act: -0.1700
Data Index: 1337275 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3522. Min Range: -5.3522
Max Act: 4.9772. Min Act: -0.1700
Data Index: 7652445 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3522. Min Range: -5.3522
Max Act: 4.8835. Min Act: -0.1700
Data Index: 442199 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3522. Min Range: -5.3522
Max Act: 4.9147. Min Act: -0.1700
Data Index: 1243916 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19