Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1686 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.5082. Min Act: -0.1700
Data Index: 2496269 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.4769. Min Act: -0.1700
Data Index: 2863052 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.4457. Min Act: -0.1700
Data Index: 183586 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.4144. Min Act: -0.1700
Data Index: 4420635 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.3206. Min Act: -0.1700
Data Index: 5233375 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.3519. Min Act: -0.1700
Data Index: 3696198 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2894. Min Act: -0.1700
Data Index: 3924514 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2894. Min Act: -0.1700
Data Index: 3863283 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2269. Min Act: -0.1700
Data Index: 5634204 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2269. Min Act: -0.1700
Data Index: 6728215 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2269. Min Act: -0.1700
Data Index: 2126112 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2269. Min Act: -0.1700
Data Index: 7474142 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2269. Min Act: -0.1700
Data Index: 3864627 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2269. Min Act: -0.1700
Data Index: 8085558 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2269. Min Act: -0.1700
Data Index: 3504783 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.2269. Min Act: -0.1700
Data Index: 1385448 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.1956. Min Act: -0.1700
Data Index: 3528200 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.1644. Min Act: -0.1700
Data Index: 6198076 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.1956. Min Act: -0.1700
Data Index: 4715443 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5082. Min Range: -4.5082
Max Act: 4.1956. Min Act: -0.1700
Data Index: 7506463 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19