Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.3890. Min Act: -0.1700
Data Index: 7989962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.3733. Min Act: -0.1700
Data Index: 7133304 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.3576. Min Act: -0.1700
Data Index: 3782671 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.3576. Min Act: -0.1700
Data Index: 1503409 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.3262. Min Act: -0.1700
Data Index: 3714676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.3105. Min Act: -0.1700
Data Index: 1518684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.3105. Min Act: -0.1700
Data Index: 7275651 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2948. Min Act: -0.1700
Data Index: 1848341 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2948. Min Act: -0.1700
Data Index: 1776382 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2948. Min Act: -0.1700
Data Index: 1768549 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2791. Min Act: -0.1700
Data Index: 5068359 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2791. Min Act: -0.1700
Data Index: 2519958 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2791. Min Act: -0.1700
Data Index: 4702846 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2791. Min Act: -0.1700
Data Index: 3527433 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2791. Min Act: -0.1700
Data Index: 2937006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2791. Min Act: -0.1700
Data Index: 8661970 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2791. Min Act: -0.1700
Data Index: 2096053 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2634. Min Act: -0.1700
Data Index: 6809413 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2634. Min Act: -0.1700
Data Index: 1229274 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3890. Min Range: -3.3890
Max Act: 3.2634. Min Act: -0.1700
Data Index: 2572974 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19