Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1004 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.5187. Min Act: -0.1700
Data Index: 641980 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.4874. Min Act: -0.1700
Data Index: 6229163 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.3937. Min Act: -0.1700
Data Index: 5415231 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.3312. Min Act: -0.1700
Data Index: 8647147 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.3624. Min Act: -0.1700
Data Index: 5415641 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2999. Min Act: -0.1700
Data Index: 6909789 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2687. Min Act: -0.1700
Data Index: 2100934 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2687. Min Act: -0.1700
Data Index: 4686270 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2999. Min Act: -0.1700
Data Index: 447328 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2687. Min Act: -0.1700
Data Index: 8764643 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2062. Min Act: -0.1700
Data Index: 4184226 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2374. Min Act: -0.1700
Data Index: 3519957 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2062. Min Act: -0.1700
Data Index: 1908338 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2062. Min Act: -0.1700
Data Index: 5221466 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2062. Min Act: -0.1700
Data Index: 4323612 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1749. Min Act: -0.1700
Data Index: 855306 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1749. Min Act: -0.1700
Data Index: 3617955 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1749. Min Act: -0.1700
Data Index: 7548908 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.1437. Min Act: -0.1700
Data Index: 3908742 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5187. Min Range: -5.5187
Max Act: 5.2062. Min Act: -0.1700
Data Index: 8832107 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19