Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.8865. Min Act: -0.1700
Data Index: 1610522 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.8865. Min Act: -0.1700
Data Index: 1780211 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.7303. Min Act: -0.1700
Data Index: 1274085 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.6053. Min Act: -0.1700
Data Index: 3951180 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.6053. Min Act: -0.1700
Data Index: 6245461 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.6053. Min Act: -0.1700
Data Index: 6396039 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.5740. Min Act: -0.1700
Data Index: 2215231 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.5428. Min Act: -0.1700
Data Index: 5738970 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.5740. Min Act: -0.1700
Data Index: 3600429 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.5115. Min Act: -0.1700
Data Index: 6855102 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.5428. Min Act: -0.1700
Data Index: 168154 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.5115. Min Act: -0.1700
Data Index: 1780207 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.4803. Min Act: -0.1700
Data Index: 746728 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.4803. Min Act: -0.1700
Data Index: 2288889 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.5115. Min Act: -0.1700
Data Index: 6118847 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.4490. Min Act: -0.1700
Data Index: 6564753 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.4490. Min Act: -0.1700
Data Index: 6919290 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.4490. Min Act: -0.1700
Data Index: 7740660 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.4490. Min Act: -0.1700
Data Index: 2279904 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8865. Min Range: -4.8865
Max Act: 4.4178. Min Act: -0.1700
Data Index: 6265492 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19