Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2066 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2645. Min Range: -5.2645
Max Act: 5.2645. Min Act: -0.1700
Data Index: 7970521 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2645. Min Range: -5.2645
Max Act: 5.2645. Min Act: -0.1700
Data Index: 2290929 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2645. Min Range: -5.2645
Max Act: 5.2332. Min Act: -0.1700
Data Index: 958764 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2645. Min Range: -5.2645
Max Act: 5.1707. Min Act: -0.1700
Data Index: 2453765 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2645. Min Range: -5.2645
Max Act: 5.1082. Min Act: -0.1700
Data Index: 8802228 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2645. Min Range: -5.2645
Max Act: 5.0770. Min Act: -0.1700
Data Index: 7174462 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.9832. Min Act: -0.1700
Data Index: 4324501 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.9832. Min Act: -0.1700
Data Index: 1842535 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.9520. Min Act: -0.1700
Data Index: 3306145 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.9520. Min Act: -0.1700
Data Index: 1143479 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.9520. Min Act: -0.1700
Data Index: 6929095 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.9520. Min Act: -0.1700
Data Index: 7133440 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.9520. Min Act: -0.1700
Data Index: 7427932 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.8895. Min Act: -0.1700
Data Index: 5728710 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.9207. Min Act: -0.1700
Data Index: 5448899 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.8895. Min Act: -0.1700
Data Index: 384168 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.8895. Min Act: -0.1700
Data Index: 8203278 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.8895. Min Act: -0.1700
Data Index: 6053796 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.8895. Min Act: -0.1700
Data Index: 1928150 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2645. Min Range: -5.2645
Max Act: 4.8895. Min Act: -0.1700
Data Index: 7426810 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19