Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4389 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.7540. Min Act: -0.1700
Data Index: 5721390 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.7228. Min Act: -0.1700
Data Index: 7120581 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.6915. Min Act: -0.1700
Data Index: 7191618 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.6603. Min Act: -0.1700
Data Index: 6647179 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.6290. Min Act: -0.1700
Data Index: 3412907 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5978. Min Act: -0.1700
Data Index: 3184947 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5665. Min Act: -0.1700
Data Index: 1993964 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5665. Min Act: -0.1700
Data Index: 7433484 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5353. Min Act: -0.1700
Data Index: 4391608 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5353. Min Act: -0.1700
Data Index: 8385313 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5040. Min Act: -0.1700
Data Index: 8273347 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5353. Min Act: -0.1700
Data Index: 486246 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5353. Min Act: -0.1700
Data Index: 7282345 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5353. Min Act: -0.1700
Data Index: 3412908 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5353. Min Act: -0.1700
Data Index: 6943207 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5040. Min Act: -0.1700
Data Index: 6797278 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5353. Min Act: -0.1700
Data Index: 2738420 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5040. Min Act: -0.1700
Data Index: 2560210 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5353. Min Act: -0.1700
Data Index: 5718744 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7540. Min Range: -4.7540
Max Act: 4.5353. Min Act: -0.1700
Data Index: 5598353 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19