Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2620 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.6827. Min Act: -0.1700
Data Index: 4340566 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.4014. Min Act: -0.1700
Data Index: 5531526 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.4014. Min Act: -0.1700
Data Index: 2592188 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.3389. Min Act: -0.1700
Data Index: 7036198 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.3389. Min Act: -0.1700
Data Index: 3291460 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.4014. Min Act: -0.1700
Data Index: 5181251 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.2764. Min Act: -0.1700
Data Index: 6950302 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.3077. Min Act: -0.1700
Data Index: 5452811 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.2764. Min Act: -0.1700
Data Index: 7970582 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.2452. Min Act: -0.1700
Data Index: 7755620 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.2139. Min Act: -0.1700
Data Index: 2406805 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.2139. Min Act: -0.1700
Data Index: 7053222 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.2139. Min Act: -0.1700
Data Index: 2613998 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.1827. Min Act: -0.1700
Data Index: 5535470 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.1514. Min Act: -0.1700
Data Index: 3023282 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.1514. Min Act: -0.1700
Data Index: 6747516 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.1514. Min Act: -0.1700
Data Index: 4794280 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.1202. Min Act: -0.1700
Data Index: 4098414 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.1202. Min Act: -0.1700
Data Index: 4721342 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6827. Min Range: -6.6827
Max Act: 6.1202. Min Act: -0.1700
Data Index: 1646714 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19