Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2331 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.5398. Min Act: -0.1700
Data Index: 3075591 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.4461. Min Act: -0.1700
Data Index: 6664849 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.4461. Min Act: -0.1700
Data Index: 2260472 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.2898. Min Act: -0.1700
Data Index: 344931 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.2273. Min Act: -0.1700
Data Index: 7391307 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.2273. Min Act: -0.1700
Data Index: 3909188 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.1336. Min Act: -0.1700
Data Index: 3163249 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.1961. Min Act: -0.1700
Data Index: 5857452 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.1336. Min Act: -0.1700
Data Index: 1288805 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.1648. Min Act: -0.1700
Data Index: 8304349 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.1336. Min Act: -0.1700
Data Index: 4639570 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.1336. Min Act: -0.1700
Data Index: 7048935 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.1023. Min Act: -0.1700
Data Index: 5342501 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.0398. Min Act: -0.1700
Data Index: 7177543 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.0711. Min Act: -0.1700
Data Index: 4653544 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.1023. Min Act: -0.1700
Data Index: 4258398 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.0398. Min Act: -0.1700
Data Index: 3082426 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.0711. Min Act: -0.1700
Data Index: 126618 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.0398. Min Act: -0.1700
Data Index: 2441149 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5398. Min Range: -6.5398
Max Act: 6.0711. Min Act: -0.1700
Data Index: 6696911 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19