Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0237. Min Range: -6.0237
Max Act: 6.0237. Min Act: -0.1700
Data Index: 1000453 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.8987. Min Act: -0.1700
Data Index: 195276 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.7424. Min Act: -0.1700
Data Index: 1285718 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.7112. Min Act: -0.1700
Data Index: 7723283 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.6799. Min Act: -0.1700
Data Index: 1456937 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.6799. Min Act: -0.1700
Data Index: 4779879 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.6799. Min Act: -0.1700
Data Index: 617270 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.6799. Min Act: -0.1700
Data Index: 7397371 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.6487. Min Act: -0.1700
Data Index: 7224494 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.6487. Min Act: -0.1700
Data Index: 7221983 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.5549. Min Act: -0.1700
Data Index: 1956099 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.5549. Min Act: -0.1700
Data Index: 7191322 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.5237. Min Act: -0.1700
Data Index: 5080151 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.5237. Min Act: -0.1700
Data Index: 4579775 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.5237. Min Act: -0.1700
Data Index: 6440529 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.4924. Min Act: -0.1700
Data Index: 222427 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.4924. Min Act: -0.1700
Data Index: 7078240 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.4924. Min Act: -0.1700
Data Index: 503048 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.4924. Min Act: -0.1700
Data Index: 4890077 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0237. Min Range: -6.0237
Max Act: 5.3987. Min Act: -0.1700
Data Index: 3662661 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19