Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2629. Min Range: -8.2629
Max Act: 8.2629. Min Act: -0.1699
Data Index: 5492810 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.9504. Min Act: -0.1700
Data Index: 336682 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.7004. Min Act: -0.1700
Data Index: 7846745 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.6379. Min Act: -0.1700
Data Index: 3021272 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.5754. Min Act: -0.1687
Data Index: 471154 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.4816. Min Act: -0.1697
Data Index: 6239214 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.4191. Min Act: -0.1698
Data Index: 6816935 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.3254. Min Act: -0.1700
Data Index: 7441508 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.3566. Min Act: -0.1700
Data Index: 7852948 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.3566. Min Act: -0.1699
Data Index: 6978861 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.3254. Min Act: -0.1700
Data Index: 4422841 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.3254. Min Act: -0.1700
Data Index: 6336660 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.3254. Min Act: -0.1700
Data Index: 6746069 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.2629. Min Act: -0.1700
Data Index: 5628161 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.2316. Min Act: -0.1700
Data Index: 7403547 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.2004. Min Act: -0.1700
Data Index: 1608072 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.1691. Min Act: -0.1700
Data Index: 8388854 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.1379. Min Act: -0.1700
Data Index: 2459863 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.1379. Min Act: -0.1700
Data Index: 3118275 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2629. Min Range: -8.2629
Max Act: 7.1066. Min Act: -0.1699
Data Index: 8302414 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19