Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1853 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.6388. Min Act: -0.1700
Data Index: 2540053 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.4513. Min Act: -0.1700
Data Index: 3182096 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.4513. Min Act: -0.1700
Data Index: 6061152 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.3575. Min Act: -0.1700
Data Index: 3372958 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.3263. Min Act: -0.1700
Data Index: 4575188 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.2950. Min Act: -0.1700
Data Index: 6755877 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.2325. Min Act: -0.1700
Data Index: 2593650 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.2325. Min Act: -0.1700
Data Index: 6693365 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.2013. Min Act: -0.1700
Data Index: 1084742 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.1388. Min Act: -0.1700
Data Index: 2726968 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.1700. Min Act: -0.1700
Data Index: 4238916 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.1075. Min Act: -0.1700
Data Index: 6988150 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.1075. Min Act: -0.1700
Data Index: 137675 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.1075. Min Act: -0.1700
Data Index: 7841078 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.1075. Min Act: -0.1700
Data Index: 1143352 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.0763. Min Act: -0.1700
Data Index: 2593653 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.0450. Min Act: -0.1700
Data Index: 6683527 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.0763. Min Act: -0.1700
Data Index: 4957873 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.0450. Min Act: -0.1700
Data Index: 3465302 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6388. Min Range: -5.6388
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6531965 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19