Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.8940. Min Act: -0.1700
Data Index: 1265733 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.7690. Min Act: -0.1700
Data Index: 5922195 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.7690. Min Act: -0.1700
Data Index: 4987385 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.6127. Min Act: -0.1700
Data Index: 3279155 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.5502. Min Act: -0.1700
Data Index: 4139150 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.5502. Min Act: -0.1700
Data Index: 2513070 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.5190. Min Act: -0.1700
Data Index: 2580602 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.5190. Min Act: -0.1700
Data Index: 848329 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.5190. Min Act: -0.1700
Data Index: 4153599 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.4877. Min Act: -0.1700
Data Index: 5060065 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.4877. Min Act: -0.1700
Data Index: 3923145 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.4564. Min Act: -0.1700
Data Index: 827658 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.4564. Min Act: -0.1700
Data Index: 134509 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.3939. Min Act: -0.1700
Data Index: 8471073 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.4252. Min Act: -0.1700
Data Index: 7694153 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.4252. Min Act: -0.1700
Data Index: 2760565 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.4252. Min Act: -0.1700
Data Index: 2150603 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.3939. Min Act: -0.1700
Data Index: 6155318 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.3939. Min Act: -0.1700
Data Index: 6315549 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8940. Min Range: -4.8940
Max Act: 4.3939. Min Act: -0.1700
Data Index: 2214288 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19