Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8652. Min Range: -8.8652
Max Act: 8.8652. Min Act: -0.1700
Data Index: 1466482 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8652. Min Range: -8.8652
Max Act: 8.4902. Min Act: -0.1700
Data Index: 3847961 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8652. Min Range: -8.8652
Max Act: 8.1777. Min Act: -0.1700
Data Index: 3911676 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8652. Min Range: -8.8652
Max Act: 8.1777. Min Act: -0.1700
Data Index: 887805 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8652. Min Range: -8.8652
Max Act: 8.1152. Min Act: -0.1700
Data Index: 2121320 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8652. Min Range: -8.8652
Max Act: 8.1152. Min Act: -0.1700
Data Index: 445950 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8652. Min Range: -8.8652
Max Act: 8.1152. Min Act: -0.1700
Data Index: 8503887 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8652. Min Range: -8.8652
Max Act: 8.0527. Min Act: -0.1700
Data Index: 4548240 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8652. Min Range: -8.8652
Max Act: 8.0527. Min Act: -0.1700
Data Index: 5954679 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.9902. Min Act: -0.1700
Data Index: 8388347 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.9902. Min Act: -0.1700
Data Index: 4593296 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.9902. Min Act: -0.1700
Data Index: 3004238 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.9902. Min Act: -0.1700
Data Index: 3163042 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.9277. Min Act: -0.1700
Data Index: 5439819 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.8652. Min Act: -0.1700
Data Index: 1030989 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.8027. Min Act: -0.1700
Data Index: 5639671 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.9277. Min Act: -0.1700
Data Index: 4593304 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.8652. Min Act: -0.1700
Data Index: 2762196 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.8652. Min Act: -0.1699
Data Index: 4995641 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8652. Min Range: -8.8652
Max Act: 7.8652. Min Act: -0.1700
Data Index: 3640719 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19