Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6228 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.2115. Min Act: -0.1700
Data Index: 3311609 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.1490. Min Act: -0.1700
Data Index: 2860372 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.1490. Min Act: -0.1700
Data Index: 6625689 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.1177. Min Act: -0.1700
Data Index: 3610819 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.0865. Min Act: -0.1700
Data Index: 1803989 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.0552. Min Act: -0.1700
Data Index: 5755115 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.0240. Min Act: -0.1700
Data Index: 4062178 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.9302. Min Act: -0.1700
Data Index: 3940652 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8990. Min Act: -0.1700
Data Index: 8414696 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8677. Min Act: -0.1700
Data Index: 7398510 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8677. Min Act: -0.1700
Data Index: 1841605 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8365. Min Act: -0.1700
Data Index: 125476 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8365. Min Act: -0.1700
Data Index: 6048594 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8052. Min Act: -0.1700
Data Index: 4923085 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8052. Min Act: -0.1700
Data Index: 3942400 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8052. Min Act: -0.1700
Data Index: 6863258 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8052. Min Act: -0.1700
Data Index: 4344499 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7427. Min Act: -0.1700
Data Index: 3414792 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7740. Min Act: -0.1700
Data Index: 2934974 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7740. Min Act: -0.1700
Data Index: 783269 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19