Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.7121. Min Act: -0.1700
Data Index: 2652494 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.7121. Min Act: -0.1700
Data Index: 5521182 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.6496. Min Act: -0.1700
Data Index: 2195329 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.6809. Min Act: -0.1700
Data Index: 3894878 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.5871. Min Act: -0.1700
Data Index: 7762527 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.6184. Min Act: -0.1700
Data Index: 8294492 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.5246. Min Act: -0.1700
Data Index: 7012901 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.5559. Min Act: -0.1700
Data Index: 8387180 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.3371. Min Act: -0.1700
Data Index: 6758036 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.3059. Min Act: -0.1700
Data Index: 3995473 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.2746. Min Act: -0.1700
Data Index: 596850 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.2434. Min Act: -0.1700
Data Index: 4889985 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.2434. Min Act: -0.1700
Data Index: 7294196 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.1496. Min Act: -0.1700
Data Index: 2576497 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.2121. Min Act: -0.1700
Data Index: 3259599 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.1809. Min Act: -0.1700
Data Index: 5457314 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.1496. Min Act: -0.1700
Data Index: 1433578 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.1809. Min Act: -0.1700
Data Index: 2392936 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.0871. Min Act: -0.1700
Data Index: 7951718 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7121. Min Range: -6.7121
Max Act: 6.1809. Min Act: -0.1700
Data Index: 229557 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19