Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4636 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.3050. Min Act: -0.1700
Data Index: 2280939 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.3050. Min Act: -0.1700
Data Index: 8434962 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.3050. Min Act: -0.1700
Data Index: 878836 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.2738. Min Act: -0.1700
Data Index: 3662043 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.2113. Min Act: -0.1700
Data Index: 5318338 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.2113. Min Act: -0.1700
Data Index: 4299823 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.1800. Min Act: -0.1700
Data Index: 8065020 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.1800. Min Act: -0.1700
Data Index: 4743473 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.1488. Min Act: -0.1700
Data Index: 3665646 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.0863. Min Act: -0.1700
Data Index: 6445618 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.1175. Min Act: -0.1700
Data Index: 182411 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.1175. Min Act: -0.1700
Data Index: 1136760 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.1175. Min Act: -0.1700
Data Index: 6922214 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.0863. Min Act: -0.1700
Data Index: 3229601 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.0238. Min Act: -0.1700
Data Index: 7395041 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.0550. Min Act: -0.1700
Data Index: 3188265 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.0550. Min Act: -0.1700
Data Index: 2653312 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.0238. Min Act: -0.1700
Data Index: 6509535 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3050. Min Range: -6.3050
Max Act: 6.0238. Min Act: -0.1700
Data Index: 6496652 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3050. Min Range: -6.3050
Max Act: 5.9925. Min Act: -0.1700
Data Index: 6849520 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19