Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5063 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.9970. Min Act: -0.1700
Data Index: 1799270 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.8720. Min Act: -0.1700
Data Index: 8824932 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.7158. Min Act: -0.1700
Data Index: 1089862 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.6845. Min Act: -0.1700
Data Index: 4152574 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.6533. Min Act: -0.1700
Data Index: 6232929 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.6220. Min Act: -0.1700
Data Index: 3057277 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.4970. Min Act: -0.1700
Data Index: 8809629 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.4658. Min Act: -0.1700
Data Index: 2477276 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.4345. Min Act: -0.1700
Data Index: 7771132 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.4033. Min Act: -0.1700
Data Index: 3265676 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.4033. Min Act: -0.1700
Data Index: 553620 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.4033. Min Act: -0.1700
Data Index: 4416384 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.3408. Min Act: -0.1700
Data Index: 7073189 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.3408. Min Act: -0.1700
Data Index: 7382360 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.3408. Min Act: -0.1700
Data Index: 5068912 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.3095. Min Act: -0.1700
Data Index: 5454124 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.2783. Min Act: -0.1700
Data Index: 1225286 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.2470. Min Act: -0.1700
Data Index: 938342 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.2470. Min Act: -0.1700
Data Index: 7892745 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9970. Min Range: -6.9970
Max Act: 6.2158. Min Act: -0.1700
Data Index: 7880334 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19