Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2253 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.4944. Min Act: -0.1700
Data Index: 6291878 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.4631. Min Act: -0.1700
Data Index: 8547641 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.4631. Min Act: -0.1700
Data Index: 7842617 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.3069. Min Act: -0.1700
Data Index: 2874726 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.3069. Min Act: -0.1700
Data Index: 2473173 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.2756. Min Act: -0.1700
Data Index: 2129720 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.2756. Min Act: -0.1700
Data Index: 1264936 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.2444. Min Act: -0.1700
Data Index: 7012619 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.2444. Min Act: -0.1700
Data Index: 8067601 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.1819. Min Act: -0.1700
Data Index: 6274427 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.1819. Min Act: -0.1700
Data Index: 1371669 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.1194. Min Act: -0.1700
Data Index: 3430267 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.1194. Min Act: -0.1700
Data Index: 5619560 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.1194. Min Act: -0.1700
Data Index: 3696201 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.0569. Min Act: -0.1700
Data Index: 5599501 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.0881. Min Act: -0.1700
Data Index: 6274429 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.0569. Min Act: -0.1700
Data Index: 7562242 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.0569. Min Act: -0.1700
Data Index: 5139698 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4944. Min Range: -5.4944
Max Act: 4.9944. Min Act: -0.1700
Data Index: 4035338 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4944. Min Range: -5.4944
Max Act: 5.0569. Min Act: -0.1700
Data Index: 1982250 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19