Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 669 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1139. Min Range: -4.1139
Max Act: 4.1139. Min Act: -0.1700
Data Index: 703340 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1139. Min Range: -4.1139
Max Act: 4.0514. Min Act: -0.1700
Data Index: 1130048 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.9107. Min Act: -0.1700
Data Index: 621663 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.6605. Min Act: -0.1700
Data Index: 3806924 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.6136. Min Act: -0.1700
Data Index: 6594979 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.6449. Min Act: -0.1700
Data Index: 4838669 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.6292. Min Act: -0.1700
Data Index: 1318936 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5979. Min Act: -0.1700
Data Index: 5264823 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5823. Min Act: -0.1700
Data Index: 4514590 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5666. Min Act: -0.1700
Data Index: 4352835 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5666. Min Act: -0.1700
Data Index: 6486731 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5666. Min Act: -0.1700
Data Index: 5001938 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5823. Min Act: -0.1700
Data Index: 238105 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5353. Min Act: -0.1700
Data Index: 502556 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5666. Min Act: -0.1700
Data Index: 7003939 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5353. Min Act: -0.1700
Data Index: 6612309 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5353. Min Act: -0.1700
Data Index: 2789439 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5666. Min Act: -0.1700
Data Index: 3195686 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5353. Min Act: -0.1700
Data Index: 5886087 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1139. Min Range: -4.1139
Max Act: 3.5040. Min Act: -0.1700
Data Index: 5467620 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19