Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1280 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.7141. Min Act: -0.1700
Data Index: 961758 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.6203. Min Act: -0.1700
Data Index: 3063880 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.5263. Min Act: -0.1700
Data Index: 7161141 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.4637. Min Act: -0.1700
Data Index: 461987 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.4167. Min Act: -0.1700
Data Index: 3384758 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.4637. Min Act: -0.1700
Data Index: 3337232 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.4323. Min Act: -0.1700
Data Index: 4274722 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.4010. Min Act: -0.1700
Data Index: 8364012 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3853. Min Act: -0.1700
Data Index: 8438668 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3696. Min Act: -0.1700
Data Index: 8584359 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.4167. Min Act: -0.1700
Data Index: 6580038 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3539. Min Act: -0.1700
Data Index: 5577767 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3853. Min Act: -0.1700
Data Index: 2602869 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3696. Min Act: -0.1700
Data Index: 7010825 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3853. Min Act: -0.1700
Data Index: 3733676 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3853. Min Act: -0.1700
Data Index: 34941 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3539. Min Act: -0.1700
Data Index: 7572253 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3696. Min Act: -0.1700
Data Index: 588592 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3696. Min Act: -0.1700
Data Index: 1549426 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7141. Min Range: -3.7141
Max Act: 3.3696. Min Act: -0.1700
Data Index: 3120041 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19