Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4740 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.5963. Min Act: -0.1700
Data Index: 8415035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.5963. Min Act: -0.1700
Data Index: 2313922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4710. Min Act: -0.1700
Data Index: 4513899 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4710. Min Act: -0.1700
Data Index: 4879566 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.5023. Min Act: -0.1700
Data Index: 4579445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.5023. Min Act: -0.1700
Data Index: 4802758 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.5023. Min Act: -0.1700
Data Index: 1518561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4710. Min Act: -0.1700
Data Index: 4733217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4710. Min Act: -0.1700
Data Index: 5239710 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4710. Min Act: -0.1700
Data Index: 1064633 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4710. Min Act: -0.1700
Data Index: 4408305 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4710. Min Act: -0.1700
Data Index: 994162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4710. Min Act: -0.1700
Data Index: 7565379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4710. Min Act: -0.1700
Data Index: 6291837 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4083. Min Act: -0.1700
Data Index: 2712489 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4083. Min Act: -0.1700
Data Index: 65118 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4397. Min Act: -0.1700
Data Index: 2497184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4397. Min Act: -0.1700
Data Index: 5249801 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4397. Min Act: -0.1700
Data Index: 1775610 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5963. Min Range: -3.5963
Max Act: 3.4397. Min Act: -0.1700
Data Index: 5589710 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19