Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1547 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.4685. Min Act: -0.1700
Data Index: 7745275 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.3123. Min Act: -0.1700
Data Index: 840731 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.2810. Min Act: -0.1700
Data Index: 4678841 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.3123. Min Act: -0.1700
Data Index: 2208663 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.2185. Min Act: -0.1700
Data Index: 6676219 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.2498. Min Act: -0.1700
Data Index: 1640407 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.1560. Min Act: -0.1700
Data Index: 2280692 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.1873. Min Act: -0.1700
Data Index: 3554751 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.1560. Min Act: -0.1700
Data Index: 4656037 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9998. Min Act: -0.1700
Data Index: 2808315 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9685. Min Act: -0.1700
Data Index: 8017604 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9998. Min Act: -0.1700
Data Index: 7901056 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9685. Min Act: -0.1700
Data Index: 1994612 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9373. Min Act: -0.1700
Data Index: 2280691 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8748. Min Act: -0.1700
Data Index: 362085 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9060. Min Act: -0.1700
Data Index: 3540613 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8435. Min Act: -0.1700
Data Index: 4984955 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8435. Min Act: -0.1700
Data Index: 4827235 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8123. Min Act: -0.1700
Data Index: 2907297 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.7810. Min Act: -0.1700
Data Index: 2747939 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19