Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2388 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0246. Min Range: -5.0246
Max Act: 5.0246. Min Act: -0.1700
Data Index: 179560 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.9308. Min Act: -0.1700
Data Index: 7275789 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.8683. Min Act: -0.1700
Data Index: 119957 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.8683. Min Act: -0.1700
Data Index: 1997478 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.8371. Min Act: -0.1700
Data Index: 7275790 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.7746. Min Act: -0.1700
Data Index: 1088275 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.7121. Min Act: -0.1700
Data Index: 6898721 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.7121. Min Act: -0.1700
Data Index: 3959668 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.7121. Min Act: -0.1700
Data Index: 6106915 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.7121. Min Act: -0.1700
Data Index: 1179077 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.6808. Min Act: -0.1700
Data Index: 7441922 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.6496. Min Act: -0.1700
Data Index: 2918449 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.6183. Min Act: -0.1700
Data Index: 2478541 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.6496. Min Act: -0.1700
Data Index: 5169613 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.6496. Min Act: -0.1700
Data Index: 6814523 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.6183. Min Act: -0.1700
Data Index: 729651 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.6183. Min Act: -0.1700
Data Index: 7188605 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.6183. Min Act: -0.1700
Data Index: 1283393 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.6183. Min Act: -0.1700
Data Index: 2149348 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0246. Min Range: -5.0246
Max Act: 4.5871. Min Act: -0.1700
Data Index: 6862109 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19