Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.7744. Min Act: -0.1700
Data Index: 1536360 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.6494. Min Act: -0.1700
Data Index: 1536359 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.6181. Min Act: -0.1700
Data Index: 4546633 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5556. Min Act: -0.1700
Data Index: 1312866 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5556. Min Act: -0.1700
Data Index: 7160330 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5556. Min Act: -0.1700
Data Index: 3007351 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5556. Min Act: -0.1700
Data Index: 1857286 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5244. Min Act: -0.1700
Data Index: 3845199 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5244. Min Act: -0.1700
Data Index: 1556800 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.5244. Min Act: -0.1700
Data Index: 3007349 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.4931. Min Act: -0.1700
Data Index: 3904363 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.4931. Min Act: -0.1700
Data Index: 4839644 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.4619. Min Act: -0.1700
Data Index: 4985115 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.4306. Min Act: -0.1700
Data Index: 8476368 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.4619. Min Act: -0.1700
Data Index: 4438380 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.4306. Min Act: -0.1700
Data Index: 7160316 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.4306. Min Act: -0.1700
Data Index: 3198046 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.4306. Min Act: -0.1700
Data Index: 1312870 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.3994. Min Act: -0.1700
Data Index: 868147 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7744. Min Range: -4.7744
Max Act: 4.3994. Min Act: -0.1700
Data Index: 1230530 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19