Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4127 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.9242. Min Act: -0.1700
Data Index: 7059263 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.7367. Min Act: -0.1700
Data Index: 440985 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6429. Min Act: -0.1700
Data Index: 1159431 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.6117. Min Act: -0.1700
Data Index: 571218 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.5179. Min Act: -0.1700
Data Index: 3428775 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.4554. Min Act: -0.1700
Data Index: 7657140 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.4242. Min Act: -0.1700
Data Index: 6257532 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.3617. Min Act: -0.1700
Data Index: 8266606 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.3617. Min Act: -0.1700
Data Index: 4651572 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.3304. Min Act: -0.1700
Data Index: 5205624 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.2992. Min Act: -0.1700
Data Index: 5602769 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.2992. Min Act: -0.1700
Data Index: 8665146 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.3304. Min Act: -0.1700
Data Index: 7596149 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.2367. Min Act: -0.1700
Data Index: 7965223 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.2679. Min Act: -0.1700
Data Index: 2173175 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.2992. Min Act: -0.1700
Data Index: 3339253 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.2679. Min Act: -0.1700
Data Index: 1448251 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.2679. Min Act: -0.1700
Data Index: 745418 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.2992. Min Act: -0.1700
Data Index: 1338891 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9242. Min Range: -5.9242
Max Act: 5.2367. Min Act: -0.1700
Data Index: 7018688 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19