Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2000 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6386. Min Range: -6.6386
Max Act: 6.6386. Min Act: -0.1700
Data Index: 8530007 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6386. Min Range: -6.6386
Max Act: 6.2636. Min Act: -0.1700
Data Index: 547768 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6386. Min Range: -6.6386
Max Act: 6.2324. Min Act: -0.1700
Data Index: 3030209 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6386. Min Range: -6.6386
Max Act: 6.2011. Min Act: -0.1700
Data Index: 5242736 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6386. Min Range: -6.6386
Max Act: 6.0136. Min Act: -0.1700
Data Index: 763377 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6386. Min Range: -6.6386
Max Act: 6.0449. Min Act: -0.1700
Data Index: 3681089 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6386. Min Range: -6.6386
Max Act: 6.0449. Min Act: -0.1700
Data Index: 7120570 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.9199. Min Act: -0.1700
Data Index: 4827822 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.9199. Min Act: -0.1700
Data Index: 3505271 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.8886. Min Act: -0.1700
Data Index: 2943059 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.8886. Min Act: -0.1700
Data Index: 1313681 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.8574. Min Act: -0.1700
Data Index: 7728720 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.8261. Min Act: -0.1700
Data Index: 2315766 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.8261. Min Act: -0.1700
Data Index: 4310161 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.7949. Min Act: -0.1700
Data Index: 5764371 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.7949. Min Act: -0.1700
Data Index: 4775543 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.7949. Min Act: -0.1700
Data Index: 4744776 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.7636. Min Act: -0.1700
Data Index: 1727187 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.7636. Min Act: -0.1700
Data Index: 7623730 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6386. Min Range: -6.6386
Max Act: 5.7949. Min Act: -0.1700
Data Index: 5111270 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19