Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.9197. Min Act: -0.1700
Data Index: 8691658 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.8884. Min Act: -0.1700
Data Index: 1064026 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.8884. Min Act: -0.1700
Data Index: 90417 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.8572. Min Act: -0.1700
Data Index: 7647932 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.8572. Min Act: -0.1700
Data Index: 7112049 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.8259. Min Act: -0.1700
Data Index: 8364557 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.8259. Min Act: -0.1700
Data Index: 3077590 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.8259. Min Act: -0.1700
Data Index: 4384720 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7947. Min Act: -0.1700
Data Index: 7611032 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7947. Min Act: -0.1700
Data Index: 5091737 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7947. Min Act: -0.1700
Data Index: 4434420 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7947. Min Act: -0.1700
Data Index: 1064029 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7947. Min Act: -0.1700
Data Index: 8665537 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7947. Min Act: -0.1700
Data Index: 669579 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7947. Min Act: -0.1700
Data Index: 8578125 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7947. Min Act: -0.1700
Data Index: 3729578 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7947. Min Act: -0.1700
Data Index: 1545241 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7634. Min Act: -0.1700
Data Index: 4783093 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7634. Min Act: -0.1700
Data Index: 6365645 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9197. Min Range: -4.9197
Max Act: 4.7634. Min Act: -0.1700
Data Index: 6506385 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19