Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5384 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.9085. Min Act: -0.1700
Data Index: 504729 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.8773. Min Act: -0.1700
Data Index: 2127207 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.8773. Min Act: -0.1700
Data Index: 5900656 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.8148. Min Act: -0.1700
Data Index: 2719239 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.7835. Min Act: -0.1700
Data Index: 6458865 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.7835. Min Act: -0.1700
Data Index: 786341 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.7210. Min Act: -0.1700
Data Index: 4157472 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.7210. Min Act: -0.1700
Data Index: 2511065 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.6273. Min Act: -0.1700
Data Index: 8376036 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.6273. Min Act: -0.1699
Data Index: 7785661 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.6273. Min Act: -0.1700
Data Index: 1865558 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.6585. Min Act: -0.1698
Data Index: 683634 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.6273. Min Act: -0.1700
Data Index: 4535443 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.5960. Min Act: -0.1700
Data Index: 3542618 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.6273. Min Act: -0.1700
Data Index: 5259548 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.5648. Min Act: -0.1700
Data Index: 3959374 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.5648. Min Act: -0.1700
Data Index: 4363621 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.5648. Min Act: -0.1700
Data Index: 2484747 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.5648. Min Act: -0.1700
Data Index: 2114501 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9085. Min Range: -5.9085
Max Act: 5.5648. Min Act: -0.1700
Data Index: 5118686 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19