Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4485 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.6485. Min Act: -0.1700
Data Index: 962842 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.5235. Min Act: -0.1700
Data Index: 8118219 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.2422. Min Act: -0.1700
Data Index: 1379733 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.2422. Min Act: -0.1700
Data Index: 610117 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.1797. Min Act: -0.1700
Data Index: 998106 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.1172. Min Act: -0.1700
Data Index: 1872839 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.1172. Min Act: -0.1700
Data Index: 4663047 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.1172. Min Act: -0.1700
Data Index: 8338663 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.0547. Min Act: -0.1700
Data Index: 4606727 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.0547. Min Act: -0.1700
Data Index: 6814904 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.0547. Min Act: -0.1700
Data Index: 1179810 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.0547. Min Act: -0.1700
Data Index: 2573385 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.0235. Min Act: -0.1700
Data Index: 1261907 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.0235. Min Act: -0.1700
Data Index: 3872741 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6485. Min Range: -6.6485
Max Act: 5.9922. Min Act: -0.1700
Data Index: 4050189 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6485. Min Range: -6.6485
Max Act: 6.0235. Min Act: -0.1700
Data Index: 2453992 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6485. Min Range: -6.6485
Max Act: 5.9922. Min Act: -0.1700
Data Index: 8705482 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6485. Min Range: -6.6485
Max Act: 5.9610. Min Act: -0.1700
Data Index: 4674651 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6485. Min Range: -6.6485
Max Act: 5.9297. Min Act: -0.1700
Data Index: 6421332 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6485. Min Range: -6.6485
Max Act: 5.9610. Min Act: -0.1700
Data Index: 6893297 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19