Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2573. Min Range: -6.2573
Max Act: 6.2573. Min Act: -0.1700
Data Index: 5045088 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.9448. Min Act: -0.1700
Data Index: 3361455 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.8823. Min Act: -0.1700
Data Index: 5782208 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.8198. Min Act: -0.1700
Data Index: 485654 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.8198. Min Act: -0.1700
Data Index: 492003 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.8198. Min Act: -0.1700
Data Index: 1704024 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.8198. Min Act: -0.1700
Data Index: 1337710 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7885. Min Act: -0.1700
Data Index: 792019 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7885. Min Act: -0.1700
Data Index: 5281355 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7573. Min Act: -0.1700
Data Index: 3840001 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7885. Min Act: -0.1700
Data Index: 2063259 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7885. Min Act: -0.1700
Data Index: 2889528 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7573. Min Act: -0.1700
Data Index: 1476435 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7260. Min Act: -0.1700
Data Index: 437757 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7573. Min Act: -0.1700
Data Index: 1218319 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7573. Min Act: -0.1700
Data Index: 5578195 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7573. Min Act: -0.1700
Data Index: 5399672 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7573. Min Act: -0.1700
Data Index: 1471498 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7573. Min Act: -0.1700
Data Index: 4824345 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2573. Min Range: -6.2573
Max Act: 5.7260. Min Act: -0.1700
Data Index: 4389900 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19