Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3909 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.8855. Min Act: -0.1700
Data Index: 5643866 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.6042. Min Act: -0.1700
Data Index: 294544 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.4792. Min Act: -0.1700
Data Index: 320709 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.4480. Min Act: -0.1700
Data Index: 2971103 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.4480. Min Act: -0.1700
Data Index: 2971104 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.4480. Min Act: -0.1700
Data Index: 3597600 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.3855. Min Act: -0.1700
Data Index: 607319 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.3542. Min Act: -0.1700
Data Index: 5889914 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.3542. Min Act: -0.1700
Data Index: 3190648 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.3230. Min Act: -0.1700
Data Index: 7723125 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.3542. Min Act: -0.1700
Data Index: 6515604 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.2605. Min Act: -0.1700
Data Index: 5035205 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.2917. Min Act: -0.1700
Data Index: 8063007 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.2605. Min Act: -0.1700
Data Index: 2083374 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.2605. Min Act: -0.1700
Data Index: 6831978 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.2292. Min Act: -0.1700
Data Index: 8656153 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.2605. Min Act: -0.1700
Data Index: 3459797 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1980. Min Act: -0.1700
Data Index: 7377623 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1667. Min Act: -0.1700
Data Index: 5404304 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8855. Min Range: -5.8855
Max Act: 5.1980. Min Act: -0.1700
Data Index: 3411289 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19