Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2499 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.2508. Min Act: -0.1700
Data Index: 6705237 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.1879. Min Act: -0.1700
Data Index: 5083121 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.1564. Min Act: -0.1700
Data Index: 4380311 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.1407. Min Act: -0.1700
Data Index: 1103917 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.1407. Min Act: -0.1700
Data Index: 1846149 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.1407. Min Act: -0.1700
Data Index: 3821529 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.1250. Min Act: -0.1700
Data Index: 617377 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0934. Min Act: -0.1700
Data Index: 3087337 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0934. Min Act: -0.1700
Data Index: 342422 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0777. Min Act: -0.1700
Data Index: 4638413 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0777. Min Act: -0.1700
Data Index: 6237893 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0303. Min Act: -0.1700
Data Index: 4275841 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0619. Min Act: -0.1700
Data Index: 8481837 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0461. Min Act: -0.1700
Data Index: 6274988 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0461. Min Act: -0.1700
Data Index: 836619 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0303. Min Act: -0.1700
Data Index: 7953074 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0461. Min Act: -0.1700
Data Index: 1044170 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0145. Min Act: -0.1700
Data Index: 3809371 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0145. Min Act: -0.1700
Data Index: 6032416 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2508. Min Range: -3.2508
Max Act: 3.0145. Min Act: -0.1700
Data Index: 406811 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19