Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1850 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1124. Min Range: -6.1124
Max Act: 6.1124. Min Act: -0.1700
Data Index: 6841205 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.9874. Min Act: -0.1700
Data Index: 62529 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7687. Min Act: -0.1700
Data Index: 1672491 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7687. Min Act: -0.1700
Data Index: 937513 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7374. Min Act: -0.1700
Data Index: 4811925 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7374. Min Act: -0.1700
Data Index: 652834 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7374. Min Act: -0.1700
Data Index: 4247322 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.7062. Min Act: -0.1700
Data Index: 7356903 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.6749. Min Act: -0.1700
Data Index: 47834 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.6437. Min Act: -0.1700
Data Index: 59298 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.6437. Min Act: -0.1700
Data Index: 2778593 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.5812. Min Act: -0.1700
Data Index: 2531218 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.5812. Min Act: -0.1700
Data Index: 3187112 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.5499. Min Act: -0.1700
Data Index: 6289070 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.5187. Min Act: -0.1700
Data Index: 6935205 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.4874. Min Act: -0.1700
Data Index: 3826119 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.5187. Min Act: -0.1700
Data Index: 7996631 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.5187. Min Act: -0.1700
Data Index: 6144573 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.4874. Min Act: -0.1700
Data Index: 6066116 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1124. Min Range: -6.1124
Max Act: 5.4874. Min Act: -0.1700
Data Index: 5567335 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19