Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3237. Min Range: -8.3237
Max Act: 8.3237. Min Act: -0.1700
Data Index: 6135308 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3237. Min Range: -8.3237
Max Act: 7.5737. Min Act: -0.1700
Data Index: 975743 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3237. Min Range: -8.3237
Max Act: 7.5112. Min Act: -0.1700
Data Index: 5513994 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3237. Min Range: -8.3237
Max Act: 7.4175. Min Act: -0.1700
Data Index: 6684610 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3237. Min Range: -8.3237
Max Act: 7.2612. Min Act: -0.1700
Data Index: 7135791 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3237. Min Range: -8.3237
Max Act: 7.2612. Min Act: -0.1700
Data Index: 6135307 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3237. Min Range: -8.3237
Max Act: 7.2612. Min Act: -0.1700
Data Index: 4082176 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3237. Min Range: -8.3237
Max Act: 7.1050. Min Act: -0.1700
Data Index: 1167876 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3237. Min Range: -8.3237
Max Act: 7.1050. Min Act: -0.1700
Data Index: 4928940 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3237. Min Range: -8.3237
Max Act: 7.0112. Min Act: -0.1700
Data Index: 4547558 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.8550. Min Act: -0.1700
Data Index: 5468257 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.8237. Min Act: -0.1700
Data Index: 7108210 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.8237. Min Act: -0.1700
Data Index: 6704856 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.8237. Min Act: -0.1700
Data Index: 1931521 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.8237. Min Act: -0.1700
Data Index: 3548657 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.7612. Min Act: -0.1700
Data Index: 5050828 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.7300. Min Act: -0.1700
Data Index: 7757364 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.7612. Min Act: -0.1700
Data Index: 3362920 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.6987. Min Act: -0.1700
Data Index: 5297104 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3237. Min Range: -8.3237
Max Act: 6.6987. Min Act: -0.1700
Data Index: 5498389 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19