Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.9607. Min Act: -0.1700
Data Index: 7765577 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.8982. Min Act: -0.1700
Data Index: 1285408 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.7420. Min Act: -0.1700
Data Index: 4187776 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.7420. Min Act: -0.1700
Data Index: 3239228 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.6482. Min Act: -0.1700
Data Index: 5283218 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.5857. Min Act: -0.1700
Data Index: 6032342 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.6482. Min Act: -0.1700
Data Index: 2053050 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.5857. Min Act: -0.1700
Data Index: 8798741 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.6170. Min Act: -0.1700
Data Index: 888128 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.5545. Min Act: -0.1700
Data Index: 2218223 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.5545. Min Act: -0.1700
Data Index: 924728 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.5545. Min Act: -0.1700
Data Index: 6008882 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.5232. Min Act: -0.1700
Data Index: 4153623 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.4920. Min Act: -0.1700
Data Index: 6091627 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.5232. Min Act: -0.1700
Data Index: 2360516 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.4920. Min Act: -0.1700
Data Index: 5876947 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.4920. Min Act: -0.1700
Data Index: 3138310 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.4607. Min Act: -0.1700
Data Index: 2130743 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.4607. Min Act: -0.1700
Data Index: 7581805 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9607. Min Range: -5.9607
Max Act: 5.4607. Min Act: -0.1700
Data Index: 5770047 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19