Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3506 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1955. Min Range: -6.1955
Max Act: 6.1955. Min Act: -0.1700
Data Index: 1204528 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.9455. Min Act: -0.1700
Data Index: 946217 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.8205. Min Act: -0.1700
Data Index: 2331350 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.8205. Min Act: -0.1700
Data Index: 3411247 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.7893. Min Act: -0.1700
Data Index: 496189 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.7580. Min Act: -0.1700
Data Index: 6028636 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.7580. Min Act: -0.1700
Data Index: 8792685 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6955. Min Act: -0.1700
Data Index: 1784360 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.7268. Min Act: -0.1700
Data Index: 4214412 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6643. Min Act: -0.1700
Data Index: 2615180 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6955. Min Act: -0.1700
Data Index: 6063061 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6955. Min Act: -0.1700
Data Index: 2791230 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6330. Min Act: -0.1700
Data Index: 2550081 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6330. Min Act: -0.1700
Data Index: 922873 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6330. Min Act: -0.1700
Data Index: 6160607 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6330. Min Act: -0.1700
Data Index: 2057640 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6018. Min Act: -0.1700
Data Index: 2795971 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6018. Min Act: -0.1700
Data Index: 4130390 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6018. Min Act: -0.1700
Data Index: 1931352 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1955. Min Range: -6.1955
Max Act: 5.6018. Min Act: -0.1700
Data Index: 7688053 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19