Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4715 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6105. Min Range: -8.6105
Max Act: 8.6105. Min Act: -0.1700
Data Index: 1646434 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6105. Min Range: -8.6105
Max Act: 8.1105. Min Act: -0.1700
Data Index: 2075748 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6105. Min Range: -8.6105
Max Act: 8.0480. Min Act: -0.1700
Data Index: 2087072 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6105. Min Range: -8.6105
Max Act: 8.0167. Min Act: -0.1700
Data Index: 4384966 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6105. Min Range: -8.6105
Max Act: 8.0480. Min Act: -0.1700
Data Index: 3592216 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6105. Min Range: -8.6105
Max Act: 8.0167. Min Act: -0.1700
Data Index: 2948600 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.9542. Min Act: -0.1700
Data Index: 2145850 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.9230. Min Act: -0.1700
Data Index: 2925365 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.9230. Min Act: -0.1700
Data Index: 7804325 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.8917. Min Act: -0.1700
Data Index: 2090629 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.8292. Min Act: -0.1700
Data Index: 2955866 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.8292. Min Act: -0.1700
Data Index: 1884328 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.8292. Min Act: -0.1700
Data Index: 6948209 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.7667. Min Act: -0.1700
Data Index: 1949422 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.7980. Min Act: -0.1700
Data Index: 2023823 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.7667. Min Act: -0.1700
Data Index: 6669166 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.7355. Min Act: -0.1700
Data Index: 781413 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.7355. Min Act: -0.1700
Data Index: 8022793 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.7042. Min Act: -0.1700
Data Index: 7047527 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6105. Min Range: -8.6105
Max Act: 7.7042. Min Act: -0.1700
Data Index: 984791 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19