Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 963 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.4648. Min Act: -0.1700
Data Index: 7089970 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.4023. Min Act: -0.1700
Data Index: 5777818 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1523. Min Act: -0.1700
Data Index: 8605943 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.1210. Min Act: -0.1700
Data Index: 1701785 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.0898. Min Act: -0.1700
Data Index: 5248127 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4648. Min Range: -5.4648
Max Act: 5.0273. Min Act: -0.1700
Data Index: 5575534 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.9960. Min Act: -0.1700
Data Index: 4798461 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.9335. Min Act: -0.1700
Data Index: 1833809 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.8710. Min Act: -0.1700
Data Index: 3592933 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.9023. Min Act: -0.1700
Data Index: 1633636 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.9023. Min Act: -0.1700
Data Index: 2842756 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.9023. Min Act: -0.1700
Data Index: 2320869 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.8085. Min Act: -0.1700
Data Index: 958163 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.7773. Min Act: -0.1700
Data Index: 1004106 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.7773. Min Act: -0.1700
Data Index: 3572678 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.7460. Min Act: -0.1700
Data Index: 4392893 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.7460. Min Act: -0.1700
Data Index: 4126448 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.7148. Min Act: -0.1700
Data Index: 5676224 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.6835. Min Act: -0.1700
Data Index: 2338221 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4648. Min Range: -5.4648
Max Act: 4.7148. Min Act: -0.1700
Data Index: 8055512 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19