Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3394 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.7321. Min Act: -0.1700
Data Index: 5778581 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.6384. Min Act: -0.1700
Data Index: 3479327 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.6696. Min Act: -0.1700
Data Index: 5249293 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.6384. Min Act: -0.1700
Data Index: 1760087 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.6071. Min Act: -0.1700
Data Index: 5429807 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.5759. Min Act: -0.1700
Data Index: 8535059 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.5759. Min Act: -0.1700
Data Index: 2717897 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.5446. Min Act: -0.1700
Data Index: 8334163 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.5446. Min Act: -0.1700
Data Index: 130351 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.5133. Min Act: -0.1700
Data Index: 4153674 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.4821. Min Act: -0.1700
Data Index: 3934372 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.4508. Min Act: -0.1700
Data Index: 1597847 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.3883. Min Act: -0.1700
Data Index: 8595089 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.3883. Min Act: -0.1700
Data Index: 3015644 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.3571. Min Act: -0.1700
Data Index: 3711006 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.3571. Min Act: -0.1700
Data Index: 5711686 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.2946. Min Act: -0.1700
Data Index: 1579381 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.3571. Min Act: -0.1700
Data Index: 1636583 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.3258. Min Act: -0.1700
Data Index: 8597315 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7321. Min Range: -4.7321
Max Act: 4.3258. Min Act: -0.1700
Data Index: 8433982 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19