Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4656 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.5382. Min Act: -0.1700
Data Index: 5628802 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.5069. Min Act: -0.1700
Data Index: 5005692 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.4132. Min Act: -0.1700
Data Index: 6328387 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.3819. Min Act: -0.1700
Data Index: 2117906 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.3819. Min Act: -0.1700
Data Index: 1131935 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.3819. Min Act: -0.1700
Data Index: 3175885 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.3507. Min Act: -0.1700
Data Index: 462850 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.3194. Min Act: -0.1700
Data Index: 4301292 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.2882. Min Act: -0.1700
Data Index: 5487128 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.2882. Min Act: -0.1700
Data Index: 535700 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.2257. Min Act: -0.1700
Data Index: 2206760 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.1632. Min Act: -0.1700
Data Index: 6875802 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.1319. Min Act: -0.1700
Data Index: 7106738 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.1319. Min Act: -0.1700
Data Index: 3474176 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.1319. Min Act: -0.1700
Data Index: 237866 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.1319. Min Act: -0.1700
Data Index: 3626487 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.0694. Min Act: -0.1700
Data Index: 4342044 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.0694. Min Act: -0.1700
Data Index: 5642133 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.1007. Min Act: -0.1700
Data Index: 7178573 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5382. Min Range: -6.5382
Max Act: 6.0694. Min Act: -0.1700
Data Index: 1564062 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19