Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.9558. Min Act: -0.1700
Data Index: 3441879 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.6433. Min Act: -0.1700
Data Index: 5961728 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.6433. Min Act: -0.1700
Data Index: 6461575 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.5808. Min Act: -0.1700
Data Index: 2060417 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.5808. Min Act: -0.1700
Data Index: 3296045 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.5808. Min Act: -0.1700
Data Index: 6941210 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.5808. Min Act: -0.1700
Data Index: 1832437 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.5183. Min Act: -0.1700
Data Index: 6308319 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.5183. Min Act: -0.1700
Data Index: 5337984 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.5183. Min Act: -0.1700
Data Index: 7540420 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.4558. Min Act: -0.1700
Data Index: 6118881 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.3933. Min Act: -0.1700
Data Index: 5782311 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.4558. Min Act: -0.1700
Data Index: 6171114 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.4558. Min Act: -0.1700
Data Index: 3752561 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.4558. Min Act: -0.1700
Data Index: 4945047 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.4558. Min Act: -0.1700
Data Index: 4896198 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.3308. Min Act: -0.1700
Data Index: 2382623 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.3933. Min Act: -0.1700
Data Index: 3661269 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.3933. Min Act: -0.1700
Data Index: 5783882 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9558. Min Range: -8.9558
Max Act: 8.3933. Min Act: -0.1700
Data Index: 915604 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19