Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.9607. Min Act: -0.1700
Data Index: 5794581 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.9607. Min Act: -0.1700
Data Index: 5892478 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.8982. Min Act: -0.1700
Data Index: 976362 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.8982. Min Act: -0.1700
Data Index: 3510158 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.8982. Min Act: -0.1700
Data Index: 2711012 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.8357. Min Act: -0.1700
Data Index: 6772714 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.8357. Min Act: -0.1700
Data Index: 3725279 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.8357. Min Act: -0.1700
Data Index: 6476650 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7732. Min Act: -0.1700
Data Index: 4976489 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 5630375 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 8696714 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.7107. Min Act: -0.1700
Data Index: 2283716 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.6482. Min Act: -0.1700
Data Index: 3348551 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.6482. Min Act: -0.1700
Data Index: 2780046 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5857. Min Act: -0.1700
Data Index: 6467406 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5857. Min Act: -0.1700
Data Index: 8748540 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5232. Min Act: -0.1700
Data Index: 6611770 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5232. Min Act: -0.1700
Data Index: 3509092 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5232. Min Act: -0.1700
Data Index: 6865451 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9607. Min Range: -8.9607
Max Act: 8.5232. Min Act: -0.1700
Data Index: 4079266 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19