Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1287 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.4463. Min Act: -0.1700
Data Index: 1491420 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3974. Min Act: -0.1700
Data Index: 843525 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3811. Min Act: -0.1700
Data Index: 3775926 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3811. Min Act: -0.1700
Data Index: 7035562 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3647. Min Act: -0.1700
Data Index: 7919256 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3647. Min Act: -0.1700
Data Index: 533726 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3484. Min Act: -0.1700
Data Index: 6391226 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3320. Min Act: -0.1700
Data Index: 1551335 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3320. Min Act: -0.1700
Data Index: 7404577 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3320. Min Act: -0.1700
Data Index: 2036010 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3155. Min Act: -0.1700
Data Index: 594678 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3320. Min Act: -0.1700
Data Index: 8394688 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3155. Min Act: -0.1700
Data Index: 1228492 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3155. Min Act: -0.1700
Data Index: 885051 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3155. Min Act: -0.1700
Data Index: 1066688 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.2991. Min Act: -0.1700
Data Index: 6729831 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3155. Min Act: -0.1700
Data Index: 6161341 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3155. Min Act: -0.1700
Data Index: 8390870 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.2991. Min Act: -0.1700
Data Index: 642615 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4463. Min Range: -2.4463
Max Act: 2.3155. Min Act: -0.1700
Data Index: 6058054 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19