Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 0 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.3509. Min Act: -0.1700
Data Index: 8767190 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.3245. Min Act: -0.1700
Data Index: 5213436 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.3333. Min Act: -0.1700
Data Index: 4123447 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.3156. Min Act: -0.1700
Data Index: 841226 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.3068. Min Act: -0.1700
Data Index: 3748308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.3068. Min Act: -0.1700
Data Index: 7997880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.3068. Min Act: -0.1700
Data Index: 5401917 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2892. Min Act: -0.1700
Data Index: 5735762 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2892. Min Act: -0.1700
Data Index: 8502964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2892. Min Act: -0.1700
Data Index: 4650554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2804. Min Act: -0.1700
Data Index: 1509500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2892. Min Act: -0.1700
Data Index: 2244208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2804. Min Act: -0.1700
Data Index: 697912 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2627. Min Act: -0.1700
Data Index: 2129372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2627. Min Act: -0.1700
Data Index: 141434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2539. Min Act: -0.1700
Data Index: 72745 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2451. Min Act: -0.1700
Data Index: 5647703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2539. Min Act: -0.1700
Data Index: 1164867 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2451. Min Act: -0.1700
Data Index: 7462819 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3509. Min Range: -1.3509
Max Act: 1.2451. Min Act: -0.1700
Data Index: 5104575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19