Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1940 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2112. Min Range: -6.2112
Max Act: 6.2112. Min Act: -0.1700
Data Index: 3439070 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2112. Min Range: -6.2112
Max Act: 6.0550. Min Act: -0.1700
Data Index: 1078233 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.9300. Min Act: -0.1700
Data Index: 5805397 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.8050. Min Act: -0.1700
Data Index: 2437510 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.7425. Min Act: -0.1700
Data Index: 7948852 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6800. Min Act: -0.1700
Data Index: 4598533 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.7425. Min Act: -0.1700
Data Index: 2995830 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.7112. Min Act: -0.1700
Data Index: 1318708 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6800. Min Act: -0.1700
Data Index: 7366287 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.7112. Min Act: -0.1700
Data Index: 7318596 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6800. Min Act: -0.1700
Data Index: 7258032 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6800. Min Act: -0.1700
Data Index: 4655094 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6800. Min Act: -0.1700
Data Index: 2570720 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6487. Min Act: -0.1700
Data Index: 7543219 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6175. Min Act: -0.1700
Data Index: 5206829 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6487. Min Act: -0.1700
Data Index: 7194425 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6487. Min Act: -0.1700
Data Index: 3199130 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.6175. Min Act: -0.1700
Data Index: 2190871 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.5862. Min Act: -0.1700
Data Index: 1664123 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2112. Min Range: -6.2112
Max Act: 5.5862. Min Act: -0.1700
Data Index: 5516074 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19