Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5072 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4572. Min Range: -6.4572
Max Act: 6.4572. Min Act: -0.1700
Data Index: 3445028 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4572. Min Range: -6.4572
Max Act: 6.1447. Min Act: -0.1700
Data Index: 5935266 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4572. Min Range: -6.4572
Max Act: 6.0822. Min Act: -0.1700
Data Index: 3445021 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4572. Min Range: -6.4572
Max Act: 6.0509. Min Act: -0.1700
Data Index: 261631 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4572. Min Range: -6.4572
Max Act: 6.0197. Min Act: -0.1700
Data Index: 5047016 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.9884. Min Act: -0.1700
Data Index: 3280251 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.9572. Min Act: -0.1700
Data Index: 6657116 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.9572. Min Act: -0.1700
Data Index: 6657118 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.9572. Min Act: -0.1700
Data Index: 3865115 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.9259. Min Act: -0.1700
Data Index: 7539108 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.8947. Min Act: -0.1700
Data Index: 1343163 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.8947. Min Act: -0.1700
Data Index: 1859020 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.9259. Min Act: -0.1700
Data Index: 2014859 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.8947. Min Act: -0.1700
Data Index: 3155760 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.8947. Min Act: -0.1700
Data Index: 5935263 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.8634. Min Act: -0.1700
Data Index: 3445026 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.8009. Min Act: -0.1700
Data Index: 7615705 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.8009. Min Act: -0.1700
Data Index: 2249212 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.8009. Min Act: -0.1700
Data Index: 4567855 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4572. Min Range: -6.4572
Max Act: 5.7697. Min Act: -0.1700
Data Index: 4339314 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19