Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.3145. Min Act: -0.1700
Data Index: 2705820 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.2517. Min Act: -0.1700
Data Index: 8631020 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.2360. Min Act: -0.1700
Data Index: 6022773 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.2203. Min Act: -0.1700
Data Index: 2939493 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1888. Min Act: -0.1700
Data Index: 6597714 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1731. Min Act: -0.1700
Data Index: 2434281 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1574. Min Act: -0.1700
Data Index: 3557569 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1574. Min Act: -0.1700
Data Index: 4968427 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1574. Min Act: -0.1700
Data Index: 139109 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1574. Min Act: -0.1700
Data Index: 4655761 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1574. Min Act: -0.1700
Data Index: 7535754 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1574. Min Act: -0.1700
Data Index: 781006 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1416. Min Act: -0.1700
Data Index: 864474 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1416. Min Act: -0.1700
Data Index: 1265170 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1416. Min Act: -0.1700
Data Index: 3904544 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1416. Min Act: -0.1700
Data Index: 2319242 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1259. Min Act: -0.1700
Data Index: 7903778 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1259. Min Act: -0.1700
Data Index: 7622406 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1259. Min Act: -0.1700
Data Index: 7609978 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3145. Min Range: -3.3145
Max Act: 3.1101. Min Act: -0.1700
Data Index: 7347337 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19