Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.5321. Min Act: -0.1700
Data Index: 3622446 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.5321. Min Act: -0.1700
Data Index: 3935168 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.5008. Min Act: -0.1700
Data Index: 4479491 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.5321. Min Act: -0.1700
Data Index: 7966413 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.4696. Min Act: -0.1700
Data Index: 7329149 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.5008. Min Act: -0.1700
Data Index: 4548741 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.4696. Min Act: -0.1700
Data Index: 1430974 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.4071. Min Act: -0.1700
Data Index: 7700982 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.4071. Min Act: -0.1700
Data Index: 2162248 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.4071. Min Act: -0.1700
Data Index: 3684933 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.4071. Min Act: -0.1700
Data Index: 4918420 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.3446. Min Act: -0.1700
Data Index: 6191069 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.3758. Min Act: -0.1700
Data Index: 459464 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.3446. Min Act: -0.1700
Data Index: 4936735 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.3446. Min Act: -0.1700
Data Index: 156499 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.2508. Min Act: -0.1700
Data Index: 5733933 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.2196. Min Act: -0.1700
Data Index: 1131071 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.2508. Min Act: -0.1700
Data Index: 3035472 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.2508. Min Act: -0.1700
Data Index: 3035474 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5321. Min Range: -5.5321
Max Act: 5.1883. Min Act: -0.1700
Data Index: 5668499 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19