Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 256 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0018. Min Range: -9.0018
Max Act: 9.0018. Min Act: -0.1700
Data Index: 6199459 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.8768. Min Act: -0.1700
Data Index: 5671383 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.7518. Min Act: -0.1700
Data Index: 6256226 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.7518. Min Act: -0.1700
Data Index: 3660082 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.6893. Min Act: -0.1700
Data Index: 4934214 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.6893. Min Act: -0.1700
Data Index: 4917989 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.6893. Min Act: -0.1700
Data Index: 4625188 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.6893. Min Act: -0.1700
Data Index: 3547860 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.6893. Min Act: -0.1700
Data Index: 646254 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.5643. Min Act: -0.1700
Data Index: 468458 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.5643. Min Act: -0.1700
Data Index: 6489727 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.5643. Min Act: -0.1700
Data Index: 8533095 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.5643. Min Act: -0.1700
Data Index: 552454 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.5643. Min Act: -0.1700
Data Index: 1544090 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.5018. Min Act: -0.1700
Data Index: 4560761 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.4393. Min Act: -0.1700
Data Index: 5431260 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.5018. Min Act: -0.1700
Data Index: 397261 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.5018. Min Act: -0.1700
Data Index: 6004964 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.4393. Min Act: -0.1700
Data Index: 275804 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0018. Min Range: -9.0018
Max Act: 8.4393. Min Act: -0.1700
Data Index: 4127104 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19