Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1868 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.9760. Min Act: -0.1700
Data Index: 5097517 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.9135. Min Act: -0.1700
Data Index: 3630733 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.8510. Min Act: -0.1700
Data Index: 3340399 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.8510. Min Act: -0.1700
Data Index: 4469912 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.8197. Min Act: -0.1700
Data Index: 8571292 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.7572. Min Act: -0.1700
Data Index: 2434831 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.7572. Min Act: -0.1700
Data Index: 3864259 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.6947. Min Act: -0.1700
Data Index: 4204715 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.6635. Min Act: -0.1700
Data Index: 3695422 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.6635. Min Act: -0.1700
Data Index: 7352933 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.6010. Min Act: -0.1700
Data Index: 5062773 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.6322. Min Act: -0.1700
Data Index: 3594506 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.6010. Min Act: -0.1700
Data Index: 6150631 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.6322. Min Act: -0.1700
Data Index: 7735379 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.5697. Min Act: -0.1700
Data Index: 2871708 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.5385. Min Act: -0.1700
Data Index: 309107 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.5385. Min Act: -0.1700
Data Index: 3617586 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.5385. Min Act: -0.1700
Data Index: 2801742 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.5072. Min Act: -0.1700
Data Index: 812843 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9760. Min Range: -5.9760
Max Act: 5.4760. Min Act: -0.1700
Data Index: 7098417 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19