Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1599 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1618. Min Range: -7.1618
Max Act: 7.1618. Min Act: -0.1700
Data Index: 1427103 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.9743. Min Act: -0.1700
Data Index: 4253037 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.9118. Min Act: -0.1700
Data Index: 953194 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.9118. Min Act: -0.1700
Data Index: 7262855 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.9118. Min Act: -0.1700
Data Index: 6494885 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.9118. Min Act: -0.1700
Data Index: 5813233 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.8493. Min Act: -0.1700
Data Index: 4396250 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.8806. Min Act: -0.1700
Data Index: 74704 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.8181. Min Act: -0.1700
Data Index: 7584316 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.8181. Min Act: -0.1700
Data Index: 4702268 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.7556. Min Act: -0.1700
Data Index: 5284492 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.8181. Min Act: -0.1700
Data Index: 4463833 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.7868. Min Act: -0.1700
Data Index: 3415591 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.7868. Min Act: -0.1700
Data Index: 369987 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.7556. Min Act: -0.1700
Data Index: 4598361 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.7556. Min Act: -0.1700
Data Index: 632445 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.7556. Min Act: -0.1700
Data Index: 5442522 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.7556. Min Act: -0.1700
Data Index: 8303969 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.7243. Min Act: -0.1700
Data Index: 2113031 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1618. Min Range: -7.1618
Max Act: 6.7243. Min Act: -0.1700
Data Index: 334416 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19