Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3669 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.5270. Min Act: -0.1700
Data Index: 3058206 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.5270. Min Act: -0.1699
Data Index: 3860979 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.4480. Min Act: -0.1699
Data Index: 3794010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3952. Min Act: -0.1700
Data Index: 4580478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3775. Min Act: -0.1699
Data Index: 822132 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3687. Min Act: -0.1700
Data Index: 7821337 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3511. Min Act: -0.1700
Data Index: 1288741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3511. Min Act: -0.1700
Data Index: 5512947 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3599. Min Act: -0.1700
Data Index: 4502673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3423. Min Act: -0.1700
Data Index: 3775508 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3423. Min Act: -0.1700
Data Index: 3687123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3246. Min Act: -0.1700
Data Index: 8269031 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3246. Min Act: -0.1700
Data Index: 2379526 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3158. Min Act: -0.1700
Data Index: 134943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3070. Min Act: -0.1700
Data Index: 7792987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3158. Min Act: -0.1699
Data Index: 5536530 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.3158. Min Act: -0.1700
Data Index: 2950085 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.2982. Min Act: -0.1700
Data Index: 2811019 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.2893. Min Act: -0.1700
Data Index: 3384544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5270. Min Range: -1.5270
Max Act: 1.2982. Min Act: -0.1700
Data Index: 555324 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19