Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4341 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.8345. Min Act: -0.1700
Data Index: 6796286 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.8032. Min Act: -0.1700
Data Index: 2686320 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.6782. Min Act: -0.1700
Data Index: 1311265 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.6782. Min Act: -0.1700
Data Index: 3832886 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.6782. Min Act: -0.1700
Data Index: 3028520 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.6157. Min Act: -0.1700
Data Index: 6782480 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.5845. Min Act: -0.1700
Data Index: 5731048 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.5845. Min Act: -0.1700
Data Index: 3212305 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.5532. Min Act: -0.1700
Data Index: 6797362 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.5220. Min Act: -0.1700
Data Index: 8133168 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4907. Min Act: -0.1700
Data Index: 8601803 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.5220. Min Act: -0.1700
Data Index: 4571044 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4907. Min Act: -0.1700
Data Index: 5053082 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.5532. Min Act: -0.1700
Data Index: 660270 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4907. Min Act: -0.1700
Data Index: 3429596 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4907. Min Act: -0.1700
Data Index: 6116167 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4907. Min Act: -0.1700
Data Index: 5187899 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4907. Min Act: -0.1700
Data Index: 6215418 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4282. Min Act: -0.1700
Data Index: 2183730 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8345. Min Range: -6.8345
Max Act: 6.4595. Min Act: -0.1700
Data Index: 3291435 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19