Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.3646. Min Act: -0.1700
Data Index: 7191049 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.1771. Min Act: -0.1700
Data Index: 1371367 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3646. Min Range: -6.3646
Max Act: 6.0209. Min Act: -0.1700
Data Index: 6688304 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8959. Min Act: -0.1700
Data Index: 1680305 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.8334. Min Act: -0.1700
Data Index: 7392365 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.7396. Min Act: -0.1700
Data Index: 2936360 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.7396. Min Act: -0.1700
Data Index: 1078972 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.7084. Min Act: -0.1700
Data Index: 4351084 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.6771. Min Act: -0.1700
Data Index: 3325495 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.6459. Min Act: -0.1700
Data Index: 2857379 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.6459. Min Act: -0.1700
Data Index: 7336454 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.6459. Min Act: -0.1700
Data Index: 2610646 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.6459. Min Act: -0.1700
Data Index: 8477507 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.6146. Min Act: -0.1700
Data Index: 3243832 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.6459. Min Act: -0.1700
Data Index: 3986653 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.5834. Min Act: -0.1700
Data Index: 8590376 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.5834. Min Act: -0.1700
Data Index: 5200656 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.5834. Min Act: -0.1700
Data Index: 8288828 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.5521. Min Act: -0.1700
Data Index: 2183581 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3646. Min Range: -6.3646
Max Act: 5.5521. Min Act: -0.1700
Data Index: 5878831 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19