Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3339 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.3638. Min Act: -0.1700
Data Index: 8735814 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.2075. Min Act: -0.1700
Data Index: 1484385 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.1763. Min Act: -0.1700
Data Index: 4345504 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0825. Min Act: -0.1700
Data Index: 4529594 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0825. Min Act: -0.1700
Data Index: 6960678 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.1138. Min Act: -0.1700
Data Index: 1664827 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.1450. Min Act: -0.1700
Data Index: 412118 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0825. Min Act: -0.1700
Data Index: 7605774 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0825. Min Act: -0.1700
Data Index: 5750619 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0825. Min Act: -0.1700
Data Index: 2509920 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0200. Min Act: -0.1700
Data Index: 7631940 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0513. Min Act: -0.1700
Data Index: 8815148 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0200. Min Act: -0.1700
Data Index: 3576375 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0513. Min Act: -0.1700
Data Index: 3164475 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0513. Min Act: -0.1700
Data Index: 2848296 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0200. Min Act: -0.1700
Data Index: 4200543 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0513. Min Act: -0.1700
Data Index: 6414917 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0200. Min Act: -0.1700
Data Index: 5484184 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3638. Min Range: -4.3638
Max Act: 4.0200. Min Act: -0.1700
Data Index: 2838966 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3638. Min Range: -4.3638
Max Act: 3.9887. Min Act: -0.1700
Data Index: 542343 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19