Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4455 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1905. Min Range: -6.1905
Max Act: 6.1905. Min Act: -0.1700
Data Index: 2312042 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1905. Min Range: -6.1905
Max Act: 6.0655. Min Act: -0.1700
Data Index: 140423 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1905. Min Range: -6.1905
Max Act: 6.0342. Min Act: -0.1700
Data Index: 634530 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1905. Min Range: -6.1905
Max Act: 6.0030. Min Act: -0.1700
Data Index: 2497505 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.9717. Min Act: -0.1700
Data Index: 7326038 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.8780. Min Act: -0.1700
Data Index: 839661 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.8467. Min Act: -0.1700
Data Index: 3641811 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2149377 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.8155. Min Act: -0.1700
Data Index: 6186804 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.7842. Min Act: -0.1700
Data Index: 2038534 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.7530. Min Act: -0.1700
Data Index: 3655259 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.7842. Min Act: -0.1700
Data Index: 5701249 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.7842. Min Act: -0.1700
Data Index: 8714248 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.7217. Min Act: -0.1700
Data Index: 7579348 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.6905. Min Act: -0.1700
Data Index: 2164263 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.6905. Min Act: -0.1700
Data Index: 7574927 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.6905. Min Act: -0.1700
Data Index: 2056175 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.6905. Min Act: -0.1700
Data Index: 3931910 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.6905. Min Act: -0.1700
Data Index: 4416875 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1905. Min Range: -6.1905
Max Act: 5.6592. Min Act: -0.1700
Data Index: 6063725 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19