Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1607 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1458. Min Range: -6.1458
Max Act: 6.1458. Min Act: -0.1700
Data Index: 2084158 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.9270. Min Act: -0.1700
Data Index: 3399484 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.8020. Min Act: -0.1700
Data Index: 6045140 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.6458. Min Act: -0.1700
Data Index: 7091955 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.4583. Min Act: -0.1700
Data Index: 444945 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.4583. Min Act: -0.1700
Data Index: 3209173 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.4270. Min Act: -0.1700
Data Index: 2731532 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.4270. Min Act: -0.1700
Data Index: 6258886 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.3645. Min Act: -0.1700
Data Index: 7826445 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.3645. Min Act: -0.1700
Data Index: 5813445 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.3645. Min Act: -0.1700
Data Index: 507897 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.3645. Min Act: -0.1700
Data Index: 4046761 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.3645. Min Act: -0.1700
Data Index: 8561993 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.3020. Min Act: -0.1700
Data Index: 7801241 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.3020. Min Act: -0.1700
Data Index: 8365977 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.3333. Min Act: -0.1700
Data Index: 7672265 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.3020. Min Act: -0.1700
Data Index: 6103944 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.2708. Min Act: -0.1700
Data Index: 712935 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.2708. Min Act: -0.1700
Data Index: 1856459 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1458. Min Range: -6.1458
Max Act: 5.2708. Min Act: -0.1700
Data Index: 518528 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19