Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2104. Min Range: -3.2104
Max Act: 3.2104. Min Act: -0.1700
Data Index: 7140441 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2104. Min Range: -3.2104
Max Act: 3.1002. Min Act: -0.1700
Data Index: 248684 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2104. Min Range: -3.2104
Max Act: 3.0686. Min Act: -0.1700
Data Index: 7140440 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2104. Min Range: -3.2104
Max Act: 3.0529. Min Act: -0.1700
Data Index: 248680 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2104. Min Range: -3.2104
Max Act: 3.0055. Min Act: -0.1700
Data Index: 974041 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2104. Min Range: -3.2104
Max Act: 3.0055. Min Act: -0.1700
Data Index: 4338890 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.9422. Min Act: -0.1700
Data Index: 1724351 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.9581. Min Act: -0.1700
Data Index: 4639756 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.9422. Min Act: -0.1700
Data Index: 3608740 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.9264. Min Act: -0.1700
Data Index: 4889768 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.9264. Min Act: -0.1700
Data Index: 4184134 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.9105. Min Act: -0.1700
Data Index: 4148913 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.8947. Min Act: -0.1700
Data Index: 8710788 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.8947. Min Act: -0.1700
Data Index: 3283257 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.8947. Min Act: -0.1700
Data Index: 637680 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.8788. Min Act: -0.1700
Data Index: 2262041 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.8947. Min Act: -0.1700
Data Index: 7727118 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.8471. Min Act: -0.1700
Data Index: 453041 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.8629. Min Act: -0.1700
Data Index: 5000471 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2104. Min Range: -3.2104
Max Act: 2.8471. Min Act: -0.1700
Data Index: 4148921 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19