Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1822 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.9855. Min Act: -0.1700
Data Index: 8348403 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.9230. Min Act: -0.1700
Data Index: 613512 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.7043. Min Act: -0.1700
Data Index: 1175923 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.6105. Min Act: -0.1700
Data Index: 8544997 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.6105. Min Act: -0.1700
Data Index: 8392642 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.5480. Min Act: -0.1700
Data Index: 7127297 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.4855. Min Act: -0.1700
Data Index: 2407024 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.4543. Min Act: -0.1700
Data Index: 7665465 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.4543. Min Act: -0.1700
Data Index: 6749522 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.4855. Min Act: -0.1700
Data Index: 7260749 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.4230. Min Act: -0.1700
Data Index: 7566842 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.4230. Min Act: -0.1700
Data Index: 1713661 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.4230. Min Act: -0.1700
Data Index: 7236219 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.3918. Min Act: -0.1700
Data Index: 125573 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.3918. Min Act: -0.1700
Data Index: 2768188 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.3605. Min Act: -0.1700
Data Index: 4606259 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.3293. Min Act: -0.1700
Data Index: 2626934 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.3293. Min Act: -0.1700
Data Index: 7543942 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.3293. Min Act: -0.1700
Data Index: 7161928 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9855. Min Range: -5.9855
Max Act: 5.2980. Min Act: -0.1700
Data Index: 3851337 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19