Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.3795. Min Act: -0.1700
Data Index: 6842280 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.2858. Min Act: -0.1700
Data Index: 4223163 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.2545. Min Act: -0.1700
Data Index: 4717865 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.1920. Min Act: -0.1700
Data Index: 2492546 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.1920. Min Act: -0.1700
Data Index: 5187272 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.1608. Min Act: -0.1700
Data Index: 6680035 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.0983. Min Act: -0.1700
Data Index: 7674361 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.0983. Min Act: -0.1700
Data Index: 7961189 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.0983. Min Act: -0.1700
Data Index: 5905008 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.0670. Min Act: -0.1700
Data Index: 317641 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.0670. Min Act: -0.1700
Data Index: 2674313 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.0670. Min Act: -0.1700
Data Index: 4401420 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.0670. Min Act: -0.1700
Data Index: 8435938 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.0358. Min Act: -0.1700
Data Index: 707026 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3795. Min Range: -6.3795
Max Act: 6.0358. Min Act: -0.1700
Data Index: 70801 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3795. Min Range: -6.3795
Max Act: 5.9733. Min Act: -0.1700
Data Index: 1118001 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3795. Min Range: -6.3795
Max Act: 5.9420. Min Act: -0.1700
Data Index: 1089110 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3795. Min Range: -6.3795
Max Act: 5.9420. Min Act: -0.1700
Data Index: 1929500 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3795. Min Range: -6.3795
Max Act: 5.9420. Min Act: -0.1700
Data Index: 4302886 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3795. Min Range: -6.3795
Max Act: 5.9420. Min Act: -0.1700
Data Index: 8357104 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19