Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2099 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.4084. Min Act: -0.1700
Data Index: 7694066 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.3772. Min Act: -0.1700
Data Index: 7350006 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.3147. Min Act: -0.1700
Data Index: 1661630 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2834. Min Act: -0.1700
Data Index: 3017095 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2834. Min Act: -0.1700
Data Index: 1206888 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2834. Min Act: -0.1700
Data Index: 1367595 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2834. Min Act: -0.1700
Data Index: 5775823 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2209. Min Act: -0.1700
Data Index: 6010920 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2209. Min Act: -0.1700
Data Index: 3315171 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1897. Min Act: -0.1700
Data Index: 358727 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2209. Min Act: -0.1700
Data Index: 2684992 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2209. Min Act: -0.1700
Data Index: 10373 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1897. Min Act: -0.1700
Data Index: 2850830 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1897. Min Act: -0.1700
Data Index: 7893548 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2209. Min Act: -0.1700
Data Index: 4561285 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1897. Min Act: -0.1700
Data Index: 1664223 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.2209. Min Act: -0.1700
Data Index: 5542077 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1897. Min Act: -0.1700
Data Index: 1104920 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1584. Min Act: -0.1700
Data Index: 5426412 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4084. Min Range: -5.4084
Max Act: 5.1584. Min Act: -0.1700
Data Index: 501383 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19