Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3159. Min Range: -6.3159
Max Act: 6.3159. Min Act: -0.1700
Data Index: 1476317 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3159. Min Range: -6.3159
Max Act: 6.1284. Min Act: -0.1700
Data Index: 6233976 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3159. Min Range: -6.3159
Max Act: 6.1284. Min Act: -0.1700
Data Index: 2567731 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3159. Min Range: -6.3159
Max Act: 6.1284. Min Act: -0.1700
Data Index: 5721123 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3159. Min Range: -6.3159
Max Act: 6.0346. Min Act: -0.1700
Data Index: 988753 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3159. Min Range: -6.3159
Max Act: 6.0346. Min Act: -0.1700
Data Index: 2092726 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.9096. Min Act: -0.1700
Data Index: 5295234 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.8784. Min Act: -0.1700
Data Index: 4231539 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.8471. Min Act: -0.1700
Data Index: 4526463 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.8159. Min Act: -0.1700
Data Index: 1969310 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.7846. Min Act: -0.1700
Data Index: 8186905 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.7846. Min Act: -0.1700
Data Index: 2984497 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.7534. Min Act: -0.1700
Data Index: 5237801 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.7534. Min Act: -0.1700
Data Index: 7625222 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.7534. Min Act: -0.1700
Data Index: 2366098 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.7534. Min Act: -0.1700
Data Index: 5079946 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.7221. Min Act: -0.1700
Data Index: 6699250 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.7221. Min Act: -0.1700
Data Index: 372668 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.6909. Min Act: -0.1700
Data Index: 4227102 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3159. Min Range: -6.3159
Max Act: 5.7221. Min Act: -0.1700
Data Index: 3351168 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19