Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1058 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3321. Min Range: -8.3321
Max Act: 8.3321. Min Act: -0.1700
Data Index: 8008339 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3321. Min Range: -8.3321
Max Act: 8.1133. Min Act: -0.1700
Data Index: 2957401 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3321. Min Range: -8.3321
Max Act: 8.0508. Min Act: -0.1700
Data Index: 2024140 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.9571. Min Act: -0.1700
Data Index: 888938 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.8633. Min Act: -0.1700
Data Index: 721832 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.8321. Min Act: -0.1700
Data Index: 4245574 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.7696. Min Act: -0.1700
Data Index: 477177 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.7696. Min Act: -0.1700
Data Index: 2509037 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.7383. Min Act: -0.1700
Data Index: 141443 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.7696. Min Act: -0.1700
Data Index: 5984400 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.6758. Min Act: -0.1700
Data Index: 6952040 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.6758. Min Act: -0.1700
Data Index: 7255096 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.6446. Min Act: -0.1700
Data Index: 1288644 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.4883. Min Act: -0.1700
Data Index: 5984397 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.4883. Min Act: -0.1700
Data Index: 5602646 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.4258. Min Act: -0.1700
Data Index: 6124364 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.3946. Min Act: -0.1700
Data Index: 8618929 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.3946. Min Act: -0.1700
Data Index: 1421818 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.3946. Min Act: -0.1700
Data Index: 528915 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3321. Min Range: -8.3321
Max Act: 7.3633. Min Act: -0.1700
Data Index: 8383370 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19