Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3082. Min Range: -6.3082
Max Act: 6.3082. Min Act: -0.1700
Data Index: 1970617 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3082. Min Range: -6.3082
Max Act: 6.1207. Min Act: -0.1700
Data Index: 5011350 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3082. Min Range: -6.3082
Max Act: 6.0269. Min Act: -0.1700
Data Index: 7532447 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3082. Min Range: -6.3082
Max Act: 6.0269. Min Act: -0.1700
Data Index: 4358869 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9644. Min Act: -0.1700
Data Index: 3428845 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9332. Min Act: -0.1700
Data Index: 488049 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9332. Min Act: -0.1700
Data Index: 4388910 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9332. Min Act: -0.1700
Data Index: 6353452 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 1283512 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 4024015 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 6409575 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 7695128 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 363808 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.8707. Min Act: -0.1700
Data Index: 797520 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 2656148 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.9019. Min Act: -0.1700
Data Index: 5655538 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.8707. Min Act: -0.1700
Data Index: 5114291 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.8707. Min Act: -0.1700
Data Index: 4690149 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.8394. Min Act: -0.1700
Data Index: 6008232 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3082. Min Range: -6.3082
Max Act: 5.8394. Min Act: -0.1700
Data Index: 3030325 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19