Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2298 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.8795. Min Act: -0.1700
Data Index: 7385268 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.4108. Min Act: -0.1700
Data Index: 1818033 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.3483. Min Act: -0.1700
Data Index: 5660924 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.3170. Min Act: -0.1700
Data Index: 2164548 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.2545. Min Act: -0.1700
Data Index: 4216281 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.1920. Min Act: -0.1700
Data Index: 5090272 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.2545. Min Act: -0.1700
Data Index: 2916240 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.2233. Min Act: -0.1700
Data Index: 6637306 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.1608. Min Act: -0.1700
Data Index: 2865254 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.1608. Min Act: -0.1700
Data Index: 6367568 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.1295. Min Act: -0.1700
Data Index: 7941076 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.1295. Min Act: -0.1700
Data Index: 2170669 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.1295. Min Act: -0.1700
Data Index: 8510469 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.1295. Min Act: -0.1700
Data Index: 5409822 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.0983. Min Act: -0.1700
Data Index: 7221563 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.1295. Min Act: -0.1700
Data Index: 350394 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.0670. Min Act: -0.1700
Data Index: 5668781 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.0983. Min Act: -0.1700
Data Index: 7545409 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.0983. Min Act: -0.1700
Data Index: 870010 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8795. Min Range: -5.8795
Max Act: 5.0670. Min Act: -0.1700
Data Index: 412841 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19