Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.8833. Min Act: -0.1700
Data Index: 4007148 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.8833. Min Act: -0.1700
Data Index: 1777192 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.8208. Min Act: -0.1700
Data Index: 5518931 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.8208. Min Act: -0.1697
Data Index: 1185921 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.8208. Min Act: -0.1700
Data Index: 4007147 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.8208. Min Act: -0.1700
Data Index: 1775255 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7896. Min Act: -0.1700
Data Index: 4691130 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7896. Min Act: -0.1700
Data Index: 1211143 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.8208. Min Act: -0.1700
Data Index: 7553648 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7896. Min Act: -0.1700
Data Index: 1538333 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7896. Min Act: -0.1700
Data Index: 1372684 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7896. Min Act: -0.1700
Data Index: 7044503 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7896. Min Act: -0.1700
Data Index: 5482968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7583. Min Act: -0.1700
Data Index: 3742264 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7583. Min Act: -0.1700
Data Index: 5742514 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7583. Min Act: -0.1700
Data Index: 7901948 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7583. Min Act: -0.1700
Data Index: 8603870 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7271. Min Act: -0.1700
Data Index: 3721057 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7271. Min Act: -0.1700
Data Index: 6644892 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8833. Min Range: -5.8833
Max Act: 5.7271. Min Act: -0.1700
Data Index: 471620 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19