Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3172 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.9211. Min Act: -0.1700
Data Index: 109208 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.8586. Min Act: -0.1700
Data Index: 5914567 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.7961. Min Act: -0.1700
Data Index: 3888688 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.7336. Min Act: -0.1700
Data Index: 2992447 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.6086. Min Act: -0.1700
Data Index: 7885335 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.6086. Min Act: -0.1700
Data Index: 1395592 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.5461. Min Act: -0.1700
Data Index: 6317341 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.5461. Min Act: -0.1700
Data Index: 5290137 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.5461. Min Act: -0.1700
Data Index: 4335208 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.5461. Min Act: -0.1700
Data Index: 810316 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.5148. Min Act: -0.1700
Data Index: 1365060 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.5148. Min Act: -0.1700
Data Index: 8704000 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.5148. Min Act: -0.1700
Data Index: 3599153 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.5148. Min Act: -0.1700
Data Index: 3749152 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.4836. Min Act: -0.1700
Data Index: 4356960 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.4836. Min Act: -0.1700
Data Index: 4776485 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.4836. Min Act: -0.1700
Data Index: 57360 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.4836. Min Act: -0.1700
Data Index: 6550955 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.4836. Min Act: -0.1700
Data Index: 1174574 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9211. Min Range: -4.9211
Max Act: 4.4836. Min Act: -0.1700
Data Index: 7375967 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19