Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3125 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3775. Min Range: -8.3775
Max Act: 8.3775. Min Act: -0.1700
Data Index: 5881095 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3775. Min Range: -8.3775
Max Act: 8.2525. Min Act: -0.1700
Data Index: 4533522 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3775. Min Range: -8.3775
Max Act: 8.0025. Min Act: -0.1700
Data Index: 8064628 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3775. Min Range: -8.3775
Max Act: 8.0025. Min Act: -0.1700
Data Index: 2430098 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3775. Min Range: -8.3775
Max Act: 8.0025. Min Act: -0.1700
Data Index: 3054347 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.9400. Min Act: -0.1700
Data Index: 8233909 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.9400. Min Act: -0.1700
Data Index: 790748 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.9400. Min Act: -0.1700
Data Index: 5340591 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.8775. Min Act: -0.1700
Data Index: 4543098 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.8775. Min Act: -0.1700
Data Index: 7205625 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.8150. Min Act: -0.1700
Data Index: 2041724 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.8150. Min Act: -0.1700
Data Index: 7899169 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.8150. Min Act: -0.1700
Data Index: 576066 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.7525. Min Act: -0.1700
Data Index: 2840331 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.7525. Min Act: -0.1700
Data Index: 876111 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.7525. Min Act: -0.1700
Data Index: 3644037 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.7525. Min Act: -0.1700
Data Index: 7268337 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.7525. Min Act: -0.1700
Data Index: 6913381 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.7525. Min Act: -0.1700
Data Index: 1524757 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3775. Min Range: -8.3775
Max Act: 7.6900. Min Act: -0.1700
Data Index: 1085347 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19