Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1802 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4515. Min Range: -8.4515
Max Act: 8.3890. Min Act: -0.1700
Data Index: 5872503 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4515. Min Range: -8.4515
Max Act: 8.4515. Min Act: -0.1700
Data Index: 5001855 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4515. Min Range: -8.4515
Max Act: 8.2015. Min Act: -0.1700
Data Index: 2105331 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4515. Min Range: -8.4515
Max Act: 8.1390. Min Act: -0.1700
Data Index: 7838962 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.9515. Min Act: -0.1700
Data Index: 7650429 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.9515. Min Act: -0.1700
Data Index: 3977907 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.9515. Min Act: -0.1700
Data Index: 4772820 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.9515. Min Act: -0.1700
Data Index: 5544628 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.9515. Min Act: -0.1700
Data Index: 3898142 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8890. Min Act: -0.1700
Data Index: 1421948 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8890. Min Act: -0.1700
Data Index: 7800276 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8890. Min Act: -0.1700
Data Index: 2231949 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8265. Min Act: -0.1700
Data Index: 3759244 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.7640. Min Act: -0.1700
Data Index: 3931635 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8265. Min Act: -0.1700
Data Index: 555673 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8265. Min Act: -0.1700
Data Index: 8102272 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8265. Min Act: -0.1700
Data Index: 8780467 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8265. Min Act: -0.1700
Data Index: 8338557 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8890. Min Act: -0.1700
Data Index: 2407361 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4515. Min Range: -8.4515
Max Act: 7.8265. Min Act: -0.1700
Data Index: 8184834 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19