Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3150 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.6275. Min Act: -0.1700
Data Index: 3760930 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.5650. Min Act: -0.1700
Data Index: 6482215 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.5025. Min Act: -0.1700
Data Index: 4649801 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.4400. Min Act: -0.1700
Data Index: 3027718 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.4400. Min Act: -0.1700
Data Index: 7334190 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.3775. Min Act: -0.1700
Data Index: 21948 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.4087. Min Act: -0.1700
Data Index: 3443477 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.3775. Min Act: -0.1700
Data Index: 8063971 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.3462. Min Act: -0.1700
Data Index: 3219824 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.3462. Min Act: -0.1700
Data Index: 4662597 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.3462. Min Act: -0.1700
Data Index: 206423 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.3150. Min Act: -0.1700
Data Index: 4837786 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.2837. Min Act: -0.1700
Data Index: 5034191 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.2837. Min Act: -0.1700
Data Index: 3083763 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.2525. Min Act: -0.1700
Data Index: 895640 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.1900. Min Act: -0.1700
Data Index: 1078050 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.1900. Min Act: -0.1700
Data Index: 6797477 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.2212. Min Act: -0.1700
Data Index: 4375390 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.1587. Min Act: -0.1700
Data Index: 2648859 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6275. Min Range: -5.6275
Max Act: 5.1587. Min Act: -0.1700
Data Index: 3885342 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19