Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1274 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.8963. Min Act: -0.1700
Data Index: 1938477 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.7088. Min Act: -0.1700
Data Index: 4161150 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.5838. Min Act: -0.1700
Data Index: 1262966 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.5213. Min Act: -0.1700
Data Index: 1480036 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.3963. Min Act: -0.1700
Data Index: 6087499 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.3963. Min Act: -0.1700
Data Index: 3472302 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.3338. Min Act: -0.1700
Data Index: 3980023 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.2713. Min Act: -0.1700
Data Index: 637128 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.3338. Min Act: -0.1700
Data Index: 4917640 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.2713. Min Act: -0.1700
Data Index: 2634730 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.2088. Min Act: -0.1700
Data Index: 4623027 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.1463. Min Act: -0.1700
Data Index: 8310219 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.0838. Min Act: -0.1700
Data Index: 7908759 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.1463. Min Act: -0.1700
Data Index: 7873535 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.1463. Min Act: -0.1700
Data Index: 6657291 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.2088. Min Act: -0.1700
Data Index: 2394812 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.1463. Min Act: -0.1700
Data Index: 8329010 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.0838. Min Act: -0.1700
Data Index: 7374813 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.0213. Min Act: -0.1700
Data Index: 4417475 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8963. Min Range: -9.8963
Max Act: 9.0213. Min Act: -0.1700
Data Index: 7920164 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19