Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4448 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7591. Min Range: -8.7591
Max Act: 8.7591. Min Act: -0.1700
Data Index: 4157335 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7591. Min Range: -8.7591
Max Act: 8.4466. Min Act: -0.1700
Data Index: 490215 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7591. Min Range: -8.7591
Max Act: 8.3841. Min Act: -0.1700
Data Index: 8316964 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7591. Min Range: -8.7591
Max Act: 8.1341. Min Act: -0.1700
Data Index: 760850 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7591. Min Range: -8.7591
Max Act: 8.0716. Min Act: -0.1700
Data Index: 7680240 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7591. Min Range: -8.7591
Max Act: 8.0091. Min Act: -0.1700
Data Index: 4725084 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.8216. Min Act: -0.1700
Data Index: 1274782 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.7904. Min Act: -0.1700
Data Index: 537655 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.7904. Min Act: -0.1700
Data Index: 544544 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.7904. Min Act: -0.1700
Data Index: 361609 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.7591. Min Act: -0.1700
Data Index: 6468380 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.7591. Min Act: -0.1700
Data Index: 2705358 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.7279. Min Act: -0.1700
Data Index: 4858526 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.7279. Min Act: -0.1700
Data Index: 8769788 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.7279. Min Act: -0.1700
Data Index: 5060191 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.7591. Min Act: -0.1700
Data Index: 55163 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.6966. Min Act: -0.1700
Data Index: 4847769 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.6654. Min Act: -0.1700
Data Index: 7179121 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.6029. Min Act: -0.1700
Data Index: 4670793 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7591. Min Range: -8.7591
Max Act: 7.6341. Min Act: -0.1700
Data Index: 3123533 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19