Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9905. Min Act: -0.1700
Data Index: 1037019 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9226. Min Act: -0.1700
Data Index: 7148787 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9226. Min Act: -0.1700
Data Index: 3445008 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 1492373 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 1432031 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 2971612 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 3447488 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 8130886 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 8107394 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 7706074 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 7357792 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 3355459 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.8885. Min Act: -0.1700
Data Index: 851378 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.8885. Min Act: -0.1700
Data Index: 6339914 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.8885. Min Act: -0.1700
Data Index: 8404171 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.9056. Min Act: -0.1700
Data Index: 4499743 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.8885. Min Act: -0.1700
Data Index: 8441312 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.8885. Min Act: -0.1700
Data Index: 8832008 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.8885. Min Act: -0.1700
Data Index: 147835 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9905. Min Range: -1.9905
Max Act: 1.8885. Min Act: -0.1700
Data Index: 4632183 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19