Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1221 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1954. Min Range: -5.1954
Max Act: 5.1954. Min Act: -0.1700
Data Index: 6321024 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1954. Min Range: -5.1954
Max Act: 5.0704. Min Act: -0.1700
Data Index: 1019244 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.9454. Min Act: -0.1700
Data Index: 8731657 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.9142. Min Act: -0.1700
Data Index: 370611 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.9142. Min Act: -0.1700
Data Index: 2264281 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.8517. Min Act: -0.1700
Data Index: 4791012 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7892. Min Act: -0.1700
Data Index: 1150819 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7892. Min Act: -0.1700
Data Index: 4791007 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7892. Min Act: -0.1700
Data Index: 555718 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7892. Min Act: -0.1700
Data Index: 717785 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7892. Min Act: -0.1700
Data Index: 5659885 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.8204. Min Act: -0.1700
Data Index: 3171411 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7892. Min Act: -0.1700
Data Index: 8730816 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7579. Min Act: -0.1700
Data Index: 2118562 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7579. Min Act: -0.1700
Data Index: 4913998 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7579. Min Act: -0.1700
Data Index: 555717 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7579. Min Act: -0.1700
Data Index: 4133433 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7267. Min Act: -0.1700
Data Index: 8572651 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7267. Min Act: -0.1700
Data Index: 7164625 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1954. Min Range: -5.1954
Max Act: 4.7267. Min Act: -0.1700
Data Index: 4672770 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19