Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2207. Min Range: -7.2207
Max Act: 7.2207. Min Act: -0.1700
Data Index: 6623780 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.6269. Min Act: -0.1700
Data Index: 1206270 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.5957. Min Act: -0.1700
Data Index: 3563494 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.4394. Min Act: -0.1700
Data Index: 2635584 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.2832. Min Act: -0.1700
Data Index: 2394854 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.2519. Min Act: -0.1700
Data Index: 2317559 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.1894. Min Act: -0.1700
Data Index: 5127537 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.1582. Min Act: -0.1700
Data Index: 748732 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.1582. Min Act: -0.1700
Data Index: 5199716 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0957. Min Act: -0.1700
Data Index: 7280014 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0957. Min Act: -0.1700
Data Index: 5626807 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0644. Min Act: -0.1700
Data Index: 4392025 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0644. Min Act: -0.1700
Data Index: 475826 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0644. Min Act: -0.1700
Data Index: 866980 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0332. Min Act: -0.1700
Data Index: 7537935 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0332. Min Act: -0.1700
Data Index: 3707257 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0019. Min Act: -0.1700
Data Index: 394516 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0019. Min Act: -0.1700
Data Index: 2033954 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.0019. Min Act: -0.1700
Data Index: 4395327 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2207. Min Range: -7.2207
Max Act: 5.9707. Min Act: -0.1700
Data Index: 5908366 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19