Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2685 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.4714. Min Act: -0.1700
Data Index: 5607613 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.4401. Min Act: -0.1700
Data Index: 1680494 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.4401. Min Act: -0.1700
Data Index: 6510590 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.4089. Min Act: -0.1700
Data Index: 7065205 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.3776. Min Act: -0.1700
Data Index: 1899750 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.3776. Min Act: -0.1700
Data Index: 919889 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.4089. Min Act: -0.1700
Data Index: 881653 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 56434 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 3391924 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 432130 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 7166400 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.3464. Min Act: -0.1700
Data Index: 3762507 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.2839. Min Act: -0.1700
Data Index: 883189 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.2839. Min Act: -0.1700
Data Index: 2068380 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.2839. Min Act: -0.1700
Data Index: 1311847 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.2526. Min Act: -0.1700
Data Index: 3302667 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.2526. Min Act: -0.1700
Data Index: 8117405 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.2526. Min Act: -0.1700
Data Index: 2914621 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.2214. Min Act: -0.1700
Data Index: 5401880 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4714. Min Range: -5.4714
Max Act: 5.2214. Min Act: -0.1700
Data Index: 3362475 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19