Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1569 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2143. Min Range: -9.2143
Max Act: 9.2143. Min Act: -0.1699
Data Index: 8554329 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2143. Min Range: -9.2143
Max Act: 9.2143. Min Act: -0.1700
Data Index: 4800193 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2143. Min Range: -9.2143
Max Act: 9.0893. Min Act: -0.1700
Data Index: 3595380 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2143. Min Range: -9.2143
Max Act: 9.0893. Min Act: -0.1700
Data Index: 7664281 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.9643. Min Act: -0.1700
Data Index: 2387777 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.9643. Min Act: -0.1700
Data Index: 4221259 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.9643. Min Act: -0.1700
Data Index: 540047 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.9018. Min Act: -0.1700
Data Index: 671178 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.9018. Min Act: -0.1700
Data Index: 6476772 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.9018. Min Act: -0.1700
Data Index: 404112 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.8393. Min Act: -0.1700
Data Index: 7615975 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.8393. Min Act: -0.1700
Data Index: 2576921 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.9018. Min Act: -0.1700
Data Index: 7112582 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.8393. Min Act: -0.1700
Data Index: 6831763 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.8393. Min Act: -0.1700
Data Index: 2512293 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.8393. Min Act: -0.1700
Data Index: 6802198 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.7768. Min Act: -0.1700
Data Index: 4891364 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.7768. Min Act: -0.1700
Data Index: 3673702 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.7768. Min Act: -0.1700
Data Index: 2629004 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2143. Min Range: -9.2143
Max Act: 8.7768. Min Act: -0.1700
Data Index: 137915 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19