Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4547 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1700. Min Range: -8.1700
Max Act: 8.1700. Min Act: -0.1700
Data Index: 1236319 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1700. Min Range: -8.1700
Max Act: 8.0450. Min Act: -0.1700
Data Index: 8051967 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.9825. Min Act: -0.1700
Data Index: 5270016 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.9200. Min Act: -0.1700
Data Index: 8027686 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.8575. Min Act: -0.1700
Data Index: 5608072 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.7637. Min Act: -0.1700
Data Index: 2511206 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.7637. Min Act: -0.1700
Data Index: 1584735 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.6700. Min Act: -0.1700
Data Index: 5421596 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.6700. Min Act: -0.1700
Data Index: 1614595 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.7012. Min Act: -0.1700
Data Index: 6005294 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.5762. Min Act: -0.1700
Data Index: 3744360 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.6075. Min Act: -0.1700
Data Index: 945673 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.5762. Min Act: -0.1700
Data Index: 7432254 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.5450. Min Act: -0.1700
Data Index: 4088705 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.5137. Min Act: -0.1700
Data Index: 3846597 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.5137. Min Act: -0.1700
Data Index: 8643963 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.5137. Min Act: -0.1700
Data Index: 988362 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.4825. Min Act: -0.1700
Data Index: 6810578 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.4825. Min Act: -0.1700
Data Index: 648367 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1700. Min Range: -8.1700
Max Act: 7.4825. Min Act: -0.1700
Data Index: 7960042 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19