Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5325 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3748. Min Range: -7.3748
Max Act: 7.3748. Min Act: -0.1700
Data Index: 5602815 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3748. Min Range: -7.3748
Max Act: 7.2498. Min Act: -0.1700
Data Index: 7768554 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3748. Min Range: -7.3748
Max Act: 7.1560. Min Act: -0.1700
Data Index: 8398086 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.9685. Min Act: -0.1700
Data Index: 8372427 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.9060. Min Act: -0.1700
Data Index: 1964145 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8435. Min Act: -0.1700
Data Index: 8070178 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8748. Min Act: -0.1700
Data Index: 5900104 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8748. Min Act: -0.1700
Data Index: 8106246 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8435. Min Act: -0.1700
Data Index: 1314308 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8748. Min Act: -0.1700
Data Index: 5707001 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8435. Min Act: -0.1700
Data Index: 1917573 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8435. Min Act: -0.1700
Data Index: 3984969 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8435. Min Act: -0.1700
Data Index: 4802022 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8123. Min Act: -0.1700
Data Index: 3970732 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8123. Min Act: -0.1700
Data Index: 3871819 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.8123. Min Act: -0.1700
Data Index: 5161102 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.7498. Min Act: -0.1700
Data Index: 3721801 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.7498. Min Act: -0.1700
Data Index: 4905165 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.7498. Min Act: -0.1700
Data Index: 2778008 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3748. Min Range: -7.3748
Max Act: 6.7498. Min Act: -0.1700
Data Index: 46416 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19