Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4924 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.9861. Min Act: -0.1700
Data Index: 6599710 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.9861. Min Act: -0.1700
Data Index: 3736844 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.7674. Min Act: -0.1700
Data Index: 8214736 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.7049. Min Act: -0.1700
Data Index: 4162397 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.6424. Min Act: -0.1700
Data Index: 8365681 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.5799. Min Act: -0.1699
Data Index: 8131690 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.5799. Min Act: -0.1700
Data Index: 2160640 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.5486. Min Act: -0.1700
Data Index: 4162396 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.5486. Min Act: -0.1700
Data Index: 1748224 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.5174. Min Act: -0.1700
Data Index: 4838426 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.4861. Min Act: -0.1700
Data Index: 5377436 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.4549. Min Act: -0.1700
Data Index: 3965736 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.4861. Min Act: -0.1700
Data Index: 2840408 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.4236. Min Act: -0.1700
Data Index: 676105 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.4236. Min Act: -0.1698
Data Index: 5425513 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.4236. Min Act: -0.1700
Data Index: 4962121 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.4549. Min Act: -0.1700
Data Index: 7971493 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.3924. Min Act: -0.1700
Data Index: 4162395 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.4236. Min Act: -0.1700
Data Index: 4999035 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9861. Min Range: -5.9861
Max Act: 5.3924. Min Act: -0.1700
Data Index: 7404957 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19