Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2365 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9890. Min Act: -0.1700
Data Index: 8729494 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9732. Min Act: -0.1700
Data Index: 5815400 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9574. Min Act: -0.1700
Data Index: 6284284 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9574. Min Act: -0.1700
Data Index: 2106318 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9257. Min Act: -0.1700
Data Index: 6308920 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9257. Min Act: -0.1700
Data Index: 1471754 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9257. Min Act: -0.1700
Data Index: 8448015 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9257. Min Act: -0.1700
Data Index: 5626898 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9257. Min Act: -0.1700
Data Index: 1827562 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9257. Min Act: -0.1700
Data Index: 2750369 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.8940. Min Act: -0.1700
Data Index: 7661153 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9098. Min Act: -0.1700
Data Index: 2826804 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.9098. Min Act: -0.1700
Data Index: 2476542 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.8940. Min Act: -0.1700
Data Index: 7356679 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.8940. Min Act: -0.1700
Data Index: 8064301 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.8940. Min Act: -0.1700
Data Index: 4297736 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.8940. Min Act: -0.1700
Data Index: 5209815 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.8940. Min Act: -0.1700
Data Index: 5473479 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.8781. Min Act: -0.1700
Data Index: 2544403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9890. Min Range: -2.9890
Max Act: 2.8940. Min Act: -0.1700
Data Index: 8554311 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19