Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3759 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.2678. Min Act: -0.1700
Data Index: 991592 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.2207. Min Act: -0.1700
Data Index: 6914685 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1735. Min Act: -0.1700
Data Index: 6945134 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1577. Min Act: -0.1700
Data Index: 7670749 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1577. Min Act: -0.1700
Data Index: 8204661 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1420. Min Act: -0.1700
Data Index: 8204663 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1263. Min Act: -0.1700
Data Index: 2423268 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1263. Min Act: -0.1700
Data Index: 541107 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1263. Min Act: -0.1700
Data Index: 2003130 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1263. Min Act: -0.1700
Data Index: 4687800 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1420. Min Act: -0.1700
Data Index: 4198439 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1105. Min Act: -0.1700
Data Index: 5231454 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1105. Min Act: -0.1700
Data Index: 3995988 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1105. Min Act: -0.1700
Data Index: 5513022 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1105. Min Act: -0.1700
Data Index: 1508853 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1105. Min Act: -0.1700
Data Index: 6699410 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.1105. Min Act: -0.1700
Data Index: 4076240 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.0790. Min Act: -0.1700
Data Index: 414291 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.0790. Min Act: -0.1700
Data Index: 5919958 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2678. Min Range: -3.2678
Max Act: 3.0790. Min Act: -0.1700
Data Index: 1116614 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19