Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1220 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.9186. Min Act: -0.1700
Data Index: 3367850 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.9029. Min Act: -0.1700
Data Index: 438368 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.8248. Min Act: -0.1700
Data Index: 7285426 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.8091. Min Act: -0.1700
Data Index: 7103338 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7778. Min Act: -0.1700
Data Index: 6246303 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.8091. Min Act: -0.1700
Data Index: 4756868 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7622. Min Act: -0.1700
Data Index: 8459661 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7935. Min Act: -0.1700
Data Index: 3038725 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7778. Min Act: -0.1700
Data Index: 316316 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7466. Min Act: -0.1700
Data Index: 5204570 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7778. Min Act: -0.1700
Data Index: 6324019 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7778. Min Act: -0.1700
Data Index: 3756033 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7309. Min Act: -0.1700
Data Index: 869215 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.6996. Min Act: -0.1700
Data Index: 5765939 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7466. Min Act: -0.1700
Data Index: 4926563 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7153. Min Act: -0.1700
Data Index: 8817827 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7309. Min Act: -0.1700
Data Index: 5504291 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7309. Min Act: -0.1700
Data Index: 4745149 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.7153. Min Act: -0.1700
Data Index: 4687417 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9186. Min Range: -3.9186
Max Act: 3.6996. Min Act: -0.1700
Data Index: 4560085 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19