Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1319 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.8931. Min Act: -0.1700
Data Index: 2405630 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.5806. Min Act: -0.1700
Data Index: 7849696 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.5181. Min Act: -0.1700
Data Index: 828608 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.2994. Min Act: -0.1700
Data Index: 8088460 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.2681. Min Act: -0.1700
Data Index: 3684504 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.2056. Min Act: -0.1700
Data Index: 5659889 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.2056. Min Act: -0.1700
Data Index: 4180995 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.1431. Min Act: -0.1700
Data Index: 108204 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.1119. Min Act: -0.1700
Data Index: 2671395 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.1119. Min Act: -0.1700
Data Index: 5630479 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.0806. Min Act: -0.1700
Data Index: 3918033 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.0806. Min Act: -0.1700
Data Index: 8114479 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.0806. Min Act: -0.1700
Data Index: 3135894 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.0181. Min Act: -0.1700
Data Index: 790322 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8931. Min Range: -6.8931
Max Act: 6.0181. Min Act: -0.1700
Data Index: 4985193 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8931. Min Range: -6.8931
Max Act: 5.9869. Min Act: -0.1700
Data Index: 4638655 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8931. Min Range: -6.8931
Max Act: 5.9869. Min Act: -0.1700
Data Index: 5659881 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8931. Min Range: -6.8931
Max Act: 5.9869. Min Act: -0.1700
Data Index: 2352064 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8931. Min Range: -6.8931
Max Act: 5.9869. Min Act: -0.1700
Data Index: 7817318 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8931. Min Range: -6.8931
Max Act: 5.9869. Min Act: -0.1700
Data Index: 4020049 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19