Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.6950. Min Act: -0.1700
Data Index: 4065597 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.6638. Min Act: -0.1700
Data Index: 4990467 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.6013. Min Act: -0.1700
Data Index: 7590660 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.6325. Min Act: -0.1700
Data Index: 1158325 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.6013. Min Act: -0.1700
Data Index: 7047962 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.5388. Min Act: -0.1700
Data Index: 4990466 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.5388. Min Act: -0.1700
Data Index: 8399848 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.5075. Min Act: -0.1700
Data Index: 4152532 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.5075. Min Act: -0.1700
Data Index: 4185922 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.5075. Min Act: -0.1700
Data Index: 1489256 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.5075. Min Act: -0.1700
Data Index: 7618917 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.5075. Min Act: -0.1700
Data Index: 4812663 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.4763. Min Act: -0.1700
Data Index: 387171 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.4763. Min Act: -0.1700
Data Index: 6271339 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.4450. Min Act: -0.1700
Data Index: 4785059 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.4138. Min Act: -0.1700
Data Index: 2824526 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.4138. Min Act: -0.1700
Data Index: 2757593 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.4138. Min Act: -0.1700
Data Index: 3526805 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.3825. Min Act: -0.1700
Data Index: 1070933 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6950. Min Range: -5.6950
Max Act: 5.4138. Min Act: -0.1700
Data Index: 1758857 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19