Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.3513. Min Act: -0.1700
Data Index: 1946466 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.3513. Min Act: -0.1700
Data Index: 4336114 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.2263. Min Act: -0.1700
Data Index: 2972005 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.1638. Min Act: -0.1700
Data Index: 8680263 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.1950. Min Act: -0.1700
Data Index: 3662067 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.1325. Min Act: -0.1700
Data Index: 6935150 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.0700. Min Act: -0.1700
Data Index: 6980927 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.0388. Min Act: -0.1700
Data Index: 3047494 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.0388. Min Act: -0.1700
Data Index: 5578851 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.0075. Min Act: -0.1700
Data Index: 4529144 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.0075. Min Act: -0.1700
Data Index: 1230635 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3513. Min Range: -5.3513
Max Act: 4.9763. Min Act: -0.1700
Data Index: 6274320 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3513. Min Range: -5.3513
Max Act: 4.9763. Min Act: -0.1700
Data Index: 2918480 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3513. Min Range: -5.3513
Max Act: 4.9450. Min Act: -0.1700
Data Index: 8300907 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3513. Min Range: -5.3513
Max Act: 5.0075. Min Act: -0.1700
Data Index: 6190007 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3513. Min Range: -5.3513
Max Act: 4.9763. Min Act: -0.1700
Data Index: 4400878 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3513. Min Range: -5.3513
Max Act: 4.9450. Min Act: -0.1700
Data Index: 5225788 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3513. Min Range: -5.3513
Max Act: 4.9138. Min Act: -0.1700
Data Index: 438480 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3513. Min Range: -5.3513
Max Act: 4.9138. Min Act: -0.1700
Data Index: 3602029 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3513. Min Range: -5.3513
Max Act: 4.8825. Min Act: -0.1700
Data Index: 4435327 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19