Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.5384. Min Act: -0.1700
Data Index: 8246594 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.4447. Min Act: -0.1700
Data Index: 2820378 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.4447. Min Act: -0.1700
Data Index: 4908005 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.3822. Min Act: -0.1700
Data Index: 3058508 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.4134. Min Act: -0.1700
Data Index: 7778037 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.3197. Min Act: -0.1700
Data Index: 5856588 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.2884. Min Act: -0.1700
Data Index: 3403114 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.2572. Min Act: -0.1700
Data Index: 1404010 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.2259. Min Act: -0.1700
Data Index: 3673039 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.2259. Min Act: -0.1700
Data Index: 8004399 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.1947. Min Act: -0.1700
Data Index: 380118 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.1634. Min Act: -0.1700
Data Index: 7621124 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.1634. Min Act: -0.1700
Data Index: 6672780 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.1322. Min Act: -0.1700
Data Index: 1862128 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.1322. Min Act: -0.1700
Data Index: 439112 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.1009. Min Act: -0.1700
Data Index: 8470317 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.0697. Min Act: -0.1700
Data Index: 5898438 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.0697. Min Act: -0.1700
Data Index: 7478135 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.1009. Min Act: -0.1700
Data Index: 3481607 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5384. Min Range: -7.5384
Max Act: 7.1009. Min Act: -0.1700
Data Index: 1558433 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19