Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3048 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2796. Min Range: -7.2796
Max Act: 7.2796. Min Act: -0.1700
Data Index: 5181983 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.9046. Min Act: -0.1700
Data Index: 247046 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.8734. Min Act: -0.1700
Data Index: 1989026 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.6859. Min Act: -0.1700
Data Index: 5045427 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.7171. Min Act: -0.1700
Data Index: 3012721 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.6546. Min Act: -0.1700
Data Index: 2031197 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.6546. Min Act: -0.1700
Data Index: 8165138 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.6234. Min Act: -0.1700
Data Index: 1876910 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.5609. Min Act: -0.1700
Data Index: 4546073 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.5609. Min Act: -0.1700
Data Index: 2096974 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.5609. Min Act: -0.1700
Data Index: 952276 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.5609. Min Act: -0.1700
Data Index: 3657428 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.4984. Min Act: -0.1700
Data Index: 8252178 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.4984. Min Act: -0.1700
Data Index: 207108 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.4671. Min Act: -0.1700
Data Index: 439806 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.3734. Min Act: -0.1700
Data Index: 7785949 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.3734. Min Act: -0.1700
Data Index: 608334 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.3421. Min Act: -0.1700
Data Index: 7680026 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.3421. Min Act: -0.1700
Data Index: 6875031 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2796. Min Range: -7.2796
Max Act: 6.3734. Min Act: -0.1700
Data Index: 4089227 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19