Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4705. Min Range: -8.4705
Max Act: 8.4705. Min Act: -0.1700
Data Index: 2716095 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4705. Min Range: -8.4705
Max Act: 8.4080. Min Act: -0.1700
Data Index: 2239997 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4705. Min Range: -8.4705
Max Act: 8.3455. Min Act: -0.1700
Data Index: 7480095 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4705. Min Range: -8.4705
Max Act: 8.3455. Min Act: -0.1700
Data Index: 4045502 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4705. Min Range: -8.4705
Max Act: 8.4392. Min Act: -0.1700
Data Index: 7261337 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4705. Min Range: -8.4705
Max Act: 8.1267. Min Act: -0.1700
Data Index: 8061102 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4705. Min Range: -8.4705
Max Act: 8.0955. Min Act: -0.1700
Data Index: 216354 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4705. Min Range: -8.4705
Max Act: 8.0642. Min Act: -0.1700
Data Index: 3659629 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.9705. Min Act: -0.1700
Data Index: 503239 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4705. Min Range: -8.4705
Max Act: 8.0017. Min Act: -0.1700
Data Index: 3384923 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.8767. Min Act: -0.1700
Data Index: 7230337 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.6267. Min Act: -0.1700
Data Index: 5594531 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.6580. Min Act: -0.1700
Data Index: 3745003 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.5017. Min Act: -0.1700
Data Index: 5040835 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.4705. Min Act: -0.1700
Data Index: 2132129 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.4392. Min Act: -0.1700
Data Index: 1915480 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.3767. Min Act: -0.1700
Data Index: 3618151 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.4392. Min Act: -0.1700
Data Index: 8724786 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.5330. Min Act: -0.1700
Data Index: 2933883 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4705. Min Range: -8.4705
Max Act: 7.3455. Min Act: -0.1700
Data Index: 6753100 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19