Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4345 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1846. Min Range: -9.1846
Max Act: 9.1846. Min Act: -0.1700
Data Index: 4973466 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1846. Min Range: -9.1846
Max Act: 9.1221. Min Act: -0.1700
Data Index: 3974748 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1846. Min Range: -9.1846
Max Act: 9.0596. Min Act: -0.1700
Data Index: 5272266 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1846. Min Range: -9.1846
Max Act: 9.1221. Min Act: -0.1700
Data Index: 2983588 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1846. Min Range: -9.1846
Max Act: 9.0596. Min Act: -0.1700
Data Index: 8796050 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.9346. Min Act: -0.1700
Data Index: 6757197 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.9971. Min Act: -0.1700
Data Index: 5115433 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.9971. Min Act: -0.1700
Data Index: 8774263 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.9971. Min Act: -0.1700
Data Index: 5783503 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.9346. Min Act: -0.1700
Data Index: 6491656 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.8721. Min Act: -0.1700
Data Index: 5048080 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.8096. Min Act: -0.1700
Data Index: 1752159 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.8096. Min Act: -0.1700
Data Index: 1401706 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.8096. Min Act: -0.1700
Data Index: 5199023 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.7471. Min Act: -0.1700
Data Index: 5981542 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.7471. Min Act: -0.1700
Data Index: 3816053 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.7471. Min Act: -0.1700
Data Index: 50253 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.6846. Min Act: -0.1700
Data Index: 7410608 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.6846. Min Act: -0.1700
Data Index: 7976839 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1846. Min Range: -9.1846
Max Act: 8.6846. Min Act: -0.1700
Data Index: 6019748 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19