Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1839. Min Range: -6.1839
Max Act: 6.1839. Min Act: -0.1700
Data Index: 1813600 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1839. Min Range: -6.1839
Max Act: 6.1839. Min Act: -0.1700
Data Index: 5524359 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1839. Min Range: -6.1839
Max Act: 6.1214. Min Act: -0.1700
Data Index: 2812858 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1839. Min Range: -6.1839
Max Act: 6.0589. Min Act: -0.1700
Data Index: 5162916 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1839. Min Range: -6.1839
Max Act: 6.0589. Min Act: -0.1700
Data Index: 8646007 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1839. Min Range: -6.1839
Max Act: 6.0276. Min Act: -0.1700
Data Index: 5665221 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9964. Min Act: -0.1700
Data Index: 1410902 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9964. Min Act: -0.1700
Data Index: 8602470 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9964. Min Act: -0.1700
Data Index: 2436323 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9964. Min Act: -0.1700
Data Index: 486660 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9651. Min Act: -0.1700
Data Index: 8019121 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9339. Min Act: -0.1700
Data Index: 6227624 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9651. Min Act: -0.1700
Data Index: 2727386 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9339. Min Act: -0.1700
Data Index: 1212966 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9339. Min Act: -0.1700
Data Index: 6940883 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9339. Min Act: -0.1700
Data Index: 5589231 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9339. Min Act: -0.1700
Data Index: 3000586 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9026. Min Act: -0.1700
Data Index: 3483163 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9026. Min Act: -0.1700
Data Index: 6294228 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1839. Min Range: -6.1839
Max Act: 5.9026. Min Act: -0.1700
Data Index: 4124323 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19