Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6065 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0705. Min Range: -6.0705
Max Act: 6.0705. Min Act: -0.1700
Data Index: 4022726 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0705. Min Range: -6.0705
Max Act: 6.0080. Min Act: -0.1700
Data Index: 7879670 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.9767. Min Act: -0.1700
Data Index: 6811711 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.7892. Min Act: -0.1700
Data Index: 947861 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.8205. Min Act: -0.1700
Data Index: 7624335 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.7892. Min Act: -0.1700
Data Index: 42275 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.7580. Min Act: -0.1700
Data Index: 507707 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.7580. Min Act: -0.1700
Data Index: 8257363 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.7580. Min Act: -0.1700
Data Index: 867562 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.7267. Min Act: -0.1700
Data Index: 5876146 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.7267. Min Act: -0.1700
Data Index: 1131516 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.7267. Min Act: -0.1700
Data Index: 2698054 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.6955. Min Act: -0.1700
Data Index: 7024977 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.6642. Min Act: -0.1700
Data Index: 5670429 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.6642. Min Act: -0.1700
Data Index: 1625001 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.6642. Min Act: -0.1700
Data Index: 7789442 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.6642. Min Act: -0.1700
Data Index: 8831883 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.6330. Min Act: -0.1700
Data Index: 2278322 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.6330. Min Act: -0.1700
Data Index: 2271445 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0705. Min Range: -6.0705
Max Act: 5.6330. Min Act: -0.1700
Data Index: 7792198 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19