Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1244 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3530. Min Act: -0.1700
Data Index: 3696882 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3530. Min Act: -0.1700
Data Index: 6944194 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3202. Min Act: -0.1700
Data Index: 6930895 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3202. Min Act: -0.1700
Data Index: 1176688 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3202. Min Act: -0.1700
Data Index: 1956837 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3038. Min Act: -0.1700
Data Index: 4572734 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3202. Min Act: -0.1700
Data Index: 2742925 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3038. Min Act: -0.1700
Data Index: 4461537 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3038. Min Act: -0.1700
Data Index: 5586093 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.3038. Min Act: -0.1700
Data Index: 5666486 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2873. Min Act: -0.1700
Data Index: 707487 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2708. Min Act: -0.1700
Data Index: 3547802 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2873. Min Act: -0.1700
Data Index: 6268048 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2873. Min Act: -0.1700
Data Index: 8587360 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2873. Min Act: -0.1700
Data Index: 5794351 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2873. Min Act: -0.1700
Data Index: 1820936 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2708. Min Act: -0.1700
Data Index: 1466538 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2708. Min Act: -0.1700
Data Index: 5129560 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2708. Min Act: -0.1700
Data Index: 6599626 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3530. Min Range: -2.3530
Max Act: 2.2708. Min Act: -0.1700
Data Index: 5978715 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19