Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5043 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.8438. Min Act: -0.1700
Data Index: 733125 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.7500. Min Act: -0.1699
Data Index: 4248690 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.6250. Min Act: -0.1700
Data Index: 2158498 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.5938. Min Act: -0.1700
Data Index: 4556819 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4688. Min Act: -0.1700
Data Index: 2529147 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.5000. Min Act: -0.1700
Data Index: 7784371 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4688. Min Act: -0.1700
Data Index: 2871589 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.5000. Min Act: -0.1700
Data Index: 5872142 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.5000. Min Act: -0.1700
Data Index: 7525362 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.5000. Min Act: -0.1700
Data Index: 2215390 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4688. Min Act: -0.1700
Data Index: 1960965 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4688. Min Act: -0.1700
Data Index: 7724647 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4688. Min Act: -0.1700
Data Index: 898153 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4688. Min Act: -0.1700
Data Index: 2317168 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4375. Min Act: -0.1700
Data Index: 2437910 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4375. Min Act: -0.1700
Data Index: 5790168 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4375. Min Act: -0.1700
Data Index: 1085462 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4375. Min Act: -0.1700
Data Index: 2584014 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4375. Min Act: -0.1697
Data Index: 5157997 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8438. Min Range: -5.8438
Max Act: 5.4375. Min Act: -0.1700
Data Index: 5138158 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19