Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.9285. Min Act: -0.1700
Data Index: 7200170 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.9127. Min Act: -0.1700
Data Index: 6967715 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8968. Min Act: -0.1700
Data Index: 6257911 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8968. Min Act: -0.1700
Data Index: 2424559 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8651. Min Act: -0.1700
Data Index: 7744773 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8651. Min Act: -0.1700
Data Index: 3987359 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8333. Min Act: -0.1700
Data Index: 7354043 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8333. Min Act: -0.1700
Data Index: 5574379 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8015. Min Act: -0.1700
Data Index: 2169665 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8174. Min Act: -0.1700
Data Index: 4834690 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8174. Min Act: -0.1700
Data Index: 3953739 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8015. Min Act: -0.1700
Data Index: 6394088 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8015. Min Act: -0.1700
Data Index: 5815271 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.8015. Min Act: -0.1700
Data Index: 1157124 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.7855. Min Act: -0.1700
Data Index: 7740223 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.7855. Min Act: -0.1700
Data Index: 3127672 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.7696. Min Act: -0.1700
Data Index: 1782823 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.7537. Min Act: -0.1700
Data Index: 4659227 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.7696. Min Act: -0.1700
Data Index: 1824513 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9285. Min Range: -2.9285
Max Act: 2.7696. Min Act: -0.1700
Data Index: 5565716 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19