Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5167 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.2726. Min Act: -0.1700
Data Index: 3145024 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.2101. Min Act: -0.1700
Data Index: 5582131 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.1789. Min Act: -0.1700
Data Index: 3284391 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.1164. Min Act: -0.1700
Data Index: 2310647 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0539. Min Act: -0.1700
Data Index: 3918028 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.9914. Min Act: -0.1700
Data Index: 28185 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.9601. Min Act: -0.1700
Data Index: 7577656 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.9601. Min Act: -0.1700
Data Index: 7256925 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.8351. Min Act: -0.1700
Data Index: 6666127 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.8351. Min Act: -0.1700
Data Index: 486607 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.8039. Min Act: -0.1700
Data Index: 4854031 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.8039. Min Act: -0.1700
Data Index: 4167048 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.8039. Min Act: -0.1700
Data Index: 3579698 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.8039. Min Act: -0.1700
Data Index: 486608 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.7414. Min Act: -0.1700
Data Index: 2862633 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.7101. Min Act: -0.1700
Data Index: 5582129 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.7101. Min Act: -0.1699
Data Index: 6764476 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.6476. Min Act: -0.1700
Data Index: 8609327 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.6789. Min Act: -0.1700
Data Index: 6666128 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.6789. Min Act: -0.1700
Data Index: 3173032 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19