Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5314 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.4119. Min Act: -0.1700
Data Index: 7498673 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.3648. Min Act: -0.1700
Data Index: 2389082 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.3178. Min Act: -0.1700
Data Index: 5125093 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.3178. Min Act: -0.1700
Data Index: 7778965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.3335. Min Act: -0.1700
Data Index: 1472998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.3021. Min Act: -0.1700
Data Index: 2556735 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.3021. Min Act: -0.1700
Data Index: 4179232 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2864. Min Act: -0.1700
Data Index: 3520757 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2864. Min Act: -0.1700
Data Index: 3587295 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2864. Min Act: -0.1700
Data Index: 4444792 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2864. Min Act: -0.1700
Data Index: 4713897 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2864. Min Act: -0.1700
Data Index: 89344 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2707. Min Act: -0.1700
Data Index: 807018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2707. Min Act: -0.1700
Data Index: 5453337 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2550. Min Act: -0.1700
Data Index: 1119577 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2550. Min Act: -0.1700
Data Index: 611022 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2550. Min Act: -0.1700
Data Index: 830502 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2550. Min Act: -0.1700
Data Index: 224182 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2550. Min Act: -0.1700
Data Index: 628891 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4119. Min Range: -3.4119
Max Act: 3.2550. Min Act: -0.1700
Data Index: 1299649 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19