Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3028 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.8613. Min Act: -0.1700
Data Index: 2956756 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.9238. Min Act: -0.1700
Data Index: 2270670 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.7988. Min Act: -0.1700
Data Index: 6767655 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.7988. Min Act: -0.1700
Data Index: 1054846 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.6113. Min Act: -0.1700
Data Index: 7771656 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.6113. Min Act: -0.1700
Data Index: 7645806 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.6113. Min Act: -0.1700
Data Index: 2845937 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.4863. Min Act: -0.1700
Data Index: 4298722 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.4863. Min Act: -0.1700
Data Index: 5048561 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.4863. Min Act: -0.1700
Data Index: 4130798 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.4238. Min Act: -0.1700
Data Index: 1658900 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.4238. Min Act: -0.1700
Data Index: 5904020 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.3613. Min Act: -0.1700
Data Index: 1973354 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.3613. Min Act: -0.1700
Data Index: 3145520 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.2988. Min Act: -0.1700
Data Index: 8799025 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.2988. Min Act: -0.1700
Data Index: 6134241 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.2363. Min Act: -0.1700
Data Index: 1868513 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.2988. Min Act: -0.1700
Data Index: 5100020 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.2363. Min Act: -0.1700
Data Index: 3651536 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9238. Min Range: -8.9238
Max Act: 8.2363. Min Act: -0.1700
Data Index: 1374796 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19