Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.6211. Min Act: -0.1700
Data Index: 5735382 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.5899. Min Act: -0.1700
Data Index: 7791011 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.6211. Min Act: -0.1700
Data Index: 6816015 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.6211. Min Act: -0.1700
Data Index: 529494 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.5586. Min Act: -0.1700
Data Index: 4468524 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.5899. Min Act: -0.1700
Data Index: 2285939 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.5586. Min Act: -0.1700
Data Index: 4780965 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.5274. Min Act: -0.1700
Data Index: 8653002 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.5274. Min Act: -0.1700
Data Index: 2557605 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4961. Min Act: -0.1700
Data Index: 7795690 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4961. Min Act: -0.1700
Data Index: 7978642 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4961. Min Act: -0.1700
Data Index: 4899203 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4649. Min Act: -0.1700
Data Index: 6937384 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4961. Min Act: -0.1700
Data Index: 6910942 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4649. Min Act: -0.1700
Data Index: 8625477 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4649. Min Act: -0.1700
Data Index: 8119335 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4649. Min Act: -0.1700
Data Index: 6797234 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4336. Min Act: -0.1700
Data Index: 5320372 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4649. Min Act: -0.1700
Data Index: 3089592 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6211. Min Range: -5.6211
Max Act: 5.4336. Min Act: -0.1700
Data Index: 7330127 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19