Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1760 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.7275. Min Act: -0.1700
Data Index: 2940745 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.5712. Min Act: -0.1700
Data Index: 6057363 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.5087. Min Act: -0.1700
Data Index: 769035 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.4462. Min Act: -0.1700
Data Index: 7639713 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.4462. Min Act: -0.1700
Data Index: 8204143 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.4150. Min Act: -0.1700
Data Index: 3899559 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.3837. Min Act: -0.1700
Data Index: 5471022 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.3837. Min Act: -0.1700
Data Index: 4088501 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.3525. Min Act: -0.1700
Data Index: 6465571 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.3525. Min Act: -0.1700
Data Index: 7297024 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.3525. Min Act: -0.1700
Data Index: 2962837 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.3525. Min Act: -0.1700
Data Index: 3518637 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.2900. Min Act: -0.1700
Data Index: 7424047 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.2900. Min Act: -0.1700
Data Index: 1502024 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.2900. Min Act: -0.1700
Data Index: 1550885 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.2900. Min Act: -0.1700
Data Index: 3853366 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.2900. Min Act: -0.1700
Data Index: 30157 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.2275. Min Act: -0.1700
Data Index: 3813771 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.2900. Min Act: -0.1700
Data Index: 1366046 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7275. Min Range: -6.7275
Max Act: 6.2587. Min Act: -0.1700
Data Index: 8710447 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19