Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 61 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.5113. Min Act: -0.1700
Data Index: 7775747 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.4800. Min Act: -0.1700
Data Index: 401314 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.4487. Min Act: -0.1700
Data Index: 5566239 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.4644. Min Act: -0.1700
Data Index: 5194569 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.4017. Min Act: -0.1700
Data Index: 1111889 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.3546. Min Act: -0.1700
Data Index: 4389505 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.3075. Min Act: -0.1700
Data Index: 6665141 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2918. Min Act: -0.1700
Data Index: 3033865 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2918. Min Act: -0.1700
Data Index: 2960577 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.3075. Min Act: -0.1700
Data Index: 5110077 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2761. Min Act: -0.1700
Data Index: 6691088 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2447. Min Act: -0.1700
Data Index: 1876621 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2761. Min Act: -0.1700
Data Index: 4233221 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2447. Min Act: -0.1700
Data Index: 3133477 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2604. Min Act: -0.1700
Data Index: 222409 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2604. Min Act: -0.1700
Data Index: 2003004 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2604. Min Act: -0.1700
Data Index: 8146046 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2290. Min Act: -0.1700
Data Index: 764433 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2447. Min Act: -0.1700
Data Index: 495784 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5113. Min Range: -3.5113
Max Act: 3.2290. Min Act: -0.1700
Data Index: 1241796 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19