Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4528 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8119. Min Range: -6.8119
Max Act: 6.8119. Min Act: -0.1700
Data Index: 8383255 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8119. Min Range: -6.8119
Max Act: 6.3744. Min Act: -0.1700
Data Index: 8514057 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8119. Min Range: -6.8119
Max Act: 6.2181. Min Act: -0.1700
Data Index: 1281915 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8119. Min Range: -6.8119
Max Act: 6.1244. Min Act: -0.1700
Data Index: 146232 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8119. Min Range: -6.8119
Max Act: 6.1244. Min Act: -0.1700
Data Index: 4661882 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.9994. Min Act: -0.1700
Data Index: 8824126 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8119. Min Range: -6.8119
Max Act: 6.0306. Min Act: -0.1700
Data Index: 2205410 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.8744. Min Act: -0.1700
Data Index: 2133745 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.8431. Min Act: -0.1700
Data Index: 5254811 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.8431. Min Act: -0.1700
Data Index: 7657821 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.7806. Min Act: -0.1700
Data Index: 3878875 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.7806. Min Act: -0.1700
Data Index: 6095318 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.7806. Min Act: -0.1700
Data Index: 5690171 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.7181. Min Act: -0.1700
Data Index: 5620830 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.7494. Min Act: -0.1700
Data Index: 7687394 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.6869. Min Act: -0.1700
Data Index: 7041331 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.7181. Min Act: -0.1700
Data Index: 60625 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.6869. Min Act: -0.1700
Data Index: 7852864 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.6869. Min Act: -0.1700
Data Index: 4694682 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8119. Min Range: -6.8119
Max Act: 5.6556. Min Act: -0.1700
Data Index: 1848448 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19