Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 172 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0489. Min Range: -4.0489
Max Act: 4.0489. Min Act: -0.1700
Data Index: 4180563 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9864. Min Act: -0.1700
Data Index: 8215318 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9864. Min Act: -0.1700
Data Index: 828415 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9239. Min Act: -0.1700
Data Index: 426532 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8926. Min Act: -0.1700
Data Index: 6527573 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.9239. Min Act: -0.1700
Data Index: 3917331 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8770. Min Act: -0.1700
Data Index: 3330928 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8770. Min Act: -0.1700
Data Index: 3098358 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8613. Min Act: -0.1700
Data Index: 7404642 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8301. Min Act: -0.1700
Data Index: 5424427 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8457. Min Act: -0.1700
Data Index: 2071537 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8457. Min Act: -0.1700
Data Index: 8150120 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8301. Min Act: -0.1700
Data Index: 7475654 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8457. Min Act: -0.1700
Data Index: 7319401 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8301. Min Act: -0.1700
Data Index: 8691828 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8301. Min Act: -0.1700
Data Index: 6974266 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8301. Min Act: -0.1700
Data Index: 2161983 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8144. Min Act: -0.1700
Data Index: 660083 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8457. Min Act: -0.1700
Data Index: 4705865 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0489. Min Range: -4.0489
Max Act: 3.8457. Min Act: -0.1700
Data Index: 2151863 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19