Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2669 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.8023. Min Act: -0.1700
Data Index: 6547012 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.8023. Min Act: -0.1700
Data Index: 4909987 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.6148. Min Act: -0.1700
Data Index: 891291 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.6148. Min Act: -0.1700
Data Index: 3214408 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.6148. Min Act: -0.1700
Data Index: 6288080 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.5523. Min Act: -0.1700
Data Index: 4077928 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.3961. Min Act: -0.1700
Data Index: 1177805 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.3336. Min Act: -0.1700
Data Index: 4024353 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.2711. Min Act: -0.1700
Data Index: 4755460 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.2711. Min Act: -0.1700
Data Index: 1487012 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.2398. Min Act: -0.1699
Data Index: 5403834 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.2711. Min Act: -0.1699
Data Index: 3764456 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.2086. Min Act: -0.1700
Data Index: 6088974 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.1773. Min Act: -0.1700
Data Index: 5591092 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.1773. Min Act: -0.1700
Data Index: 7159840 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.1461. Min Act: -0.1700
Data Index: 6669701 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.1461. Min Act: -0.1700
Data Index: 5506103 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.1773. Min Act: -0.1700
Data Index: 3528329 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.0836. Min Act: -0.1700
Data Index: 1471289 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8023. Min Range: -7.8023
Max Act: 7.1148. Min Act: -0.1700
Data Index: 5435901 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19