Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1931 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3333. Min Range: -7.3333
Max Act: 7.3333. Min Act: -0.1700
Data Index: 634564 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.8333. Min Act: -0.1700
Data Index: 1445124 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.7083. Min Act: -0.1700
Data Index: 4053644 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.6146. Min Act: -0.1700
Data Index: 8636758 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.5833. Min Act: -0.1700
Data Index: 4258015 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.5833. Min Act: -0.1700
Data Index: 3337095 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.5833. Min Act: -0.1700
Data Index: 184783 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.5833. Min Act: -0.1700
Data Index: 2040170 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.5521. Min Act: -0.1700
Data Index: 1294856 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.5208. Min Act: -0.1700
Data Index: 2378501 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.4583. Min Act: -0.1700
Data Index: 2808852 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.4271. Min Act: -0.1700
Data Index: 992822 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.3958. Min Act: -0.1700
Data Index: 2184450 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.3646. Min Act: -0.1700
Data Index: 3027462 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.3333. Min Act: -0.1700
Data Index: 14511 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.3646. Min Act: -0.1700
Data Index: 4118556 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.3333. Min Act: -0.1700
Data Index: 2096015 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.3333. Min Act: -0.1700
Data Index: 4756703 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.3021. Min Act: -0.1700
Data Index: 2562702 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3333. Min Range: -7.3333
Max Act: 6.3021. Min Act: -0.1700
Data Index: 8426623 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19