Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 3575746 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.4714. Min Act: -0.1700
Data Index: 1715791 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.3777. Min Act: -0.1700
Data Index: 7626756 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.3464. Min Act: -0.1700
Data Index: 308666 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.2839. Min Act: -0.1700
Data Index: 2632034 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.2839. Min Act: -0.1700
Data Index: 7140181 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.2527. Min Act: -0.1700
Data Index: 4203219 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.2527. Min Act: -0.1700
Data Index: 6519361 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.2527. Min Act: -0.1700
Data Index: 4190310 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.2214. Min Act: -0.1700
Data Index: 308541 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.2214. Min Act: -0.1700
Data Index: 162531 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.1589. Min Act: -0.1700
Data Index: 2382920 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.1277. Min Act: -0.1700
Data Index: 4474507 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.1277. Min Act: -0.1700
Data Index: 8398 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.0964. Min Act: -0.1700
Data Index: 3655335 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.0964. Min Act: -0.1700
Data Index: 1062806 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.0964. Min Act: -0.1700
Data Index: 7030542 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.0964. Min Act: -0.1700
Data Index: 5076133 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.0964. Min Act: -0.1700
Data Index: 5452784 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4714. Min Range: -7.4714
Max Act: 7.0652. Min Act: -0.1700
Data Index: 5392876 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19