Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.8264. Min Act: -0.1700
Data Index: 5559933 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.7639. Min Act: -0.1700
Data Index: 1855648 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.7639. Min Act: -0.1700
Data Index: 2178441 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.7639. Min Act: -0.1700
Data Index: 1663519 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.7326. Min Act: -0.1700
Data Index: 7159075 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.7014. Min Act: -0.1700
Data Index: 8492240 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.7014. Min Act: -0.1700
Data Index: 5095249 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.6389. Min Act: -0.1700
Data Index: 263122 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.5764. Min Act: -0.1700
Data Index: 6701578 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.5764. Min Act: -0.1700
Data Index: 6151534 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.5764. Min Act: -0.1700
Data Index: 1655435 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.5139. Min Act: -0.1700
Data Index: 6775314 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.5139. Min Act: -0.1700
Data Index: 8804615 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.4826. Min Act: -0.1700
Data Index: 6822129 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.4826. Min Act: -0.1700
Data Index: 2771646 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.4201. Min Act: -0.1700
Data Index: 4993587 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.4514. Min Act: -0.1700
Data Index: 3521 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.4514. Min Act: -0.1700
Data Index: 2667544 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.4514. Min Act: -0.1700
Data Index: 632493 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8264. Min Range: -4.8264
Max Act: 4.4514. Min Act: -0.1700
Data Index: 7031706 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19