Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.7972. Min Act: -0.1700
Data Index: 4600820 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.7815. Min Act: -0.1700
Data Index: 3651299 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.7659. Min Act: -0.1700
Data Index: 2330064 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.7190. Min Act: -0.1700
Data Index: 1766048 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.7033. Min Act: -0.1700
Data Index: 5688991 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.6877. Min Act: -0.1700
Data Index: 3661495 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.6720. Min Act: -0.1700
Data Index: 6691746 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.6720. Min Act: -0.1700
Data Index: 6590168 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.6408. Min Act: -0.1700
Data Index: 2882742 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.6095. Min Act: -0.1700
Data Index: 4228719 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.5782. Min Act: -0.1700
Data Index: 7575224 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.6095. Min Act: -0.1700
Data Index: 3120995 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.6095. Min Act: -0.1700
Data Index: 4477675 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.5782. Min Act: -0.1700
Data Index: 1766047 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.5782. Min Act: -0.1700
Data Index: 6933912 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.5938. Min Act: -0.1700
Data Index: 838736 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.5938. Min Act: -0.1700
Data Index: 6417008 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.5625. Min Act: -0.1700
Data Index: 1028214 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.5312. Min Act: -0.1700
Data Index: 5440919 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7972. Min Range: -3.7972
Max Act: 3.5625. Min Act: -0.1700
Data Index: 2823985 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19