Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1885 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.4213. Min Act: -0.1700
Data Index: 1312387 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3586. Min Act: -0.1700
Data Index: 4945097 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3900. Min Act: -0.1700
Data Index: 8274158 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3743. Min Act: -0.1700
Data Index: 4990291 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3429. Min Act: -0.1700
Data Index: 7902047 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3272. Min Act: -0.1700
Data Index: 8694522 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3272. Min Act: -0.1700
Data Index: 7709621 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3272. Min Act: -0.1700
Data Index: 4119251 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2958. Min Act: -0.1700
Data Index: 582587 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2958. Min Act: -0.1700
Data Index: 337354 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3429. Min Act: -0.1700
Data Index: 2469191 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2958. Min Act: -0.1700
Data Index: 3304828 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3115. Min Act: -0.1700
Data Index: 4112143 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3115. Min Act: -0.1700
Data Index: 6699415 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2801. Min Act: -0.1700
Data Index: 3539160 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2801. Min Act: -0.1700
Data Index: 8127918 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2487. Min Act: -0.1700
Data Index: 2695785 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2487. Min Act: -0.1700
Data Index: 1205600 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2644. Min Act: -0.1700
Data Index: 8274161 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2173. Min Act: -0.1700
Data Index: 5658261 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19