Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2808 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4628. Min Act: -0.1700
Data Index: 1122859 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4785. Min Act: -0.1700
Data Index: 1173759 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4628. Min Act: -0.1700
Data Index: 8101205 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4628. Min Act: -0.1700
Data Index: 4089423 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4472. Min Act: -0.1700
Data Index: 8536251 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4158. Min Act: -0.1700
Data Index: 3547639 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4158. Min Act: -0.1700
Data Index: 1552787 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4158. Min Act: -0.1700
Data Index: 5034623 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4002. Min Act: -0.1700
Data Index: 8188772 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4158. Min Act: -0.1700
Data Index: 730368 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.4002. Min Act: -0.1700
Data Index: 6478711 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.3845. Min Act: -0.1700
Data Index: 4765133 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.3688. Min Act: -0.1700
Data Index: 1883336 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.3845. Min Act: -0.1700
Data Index: 3523000 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.3845. Min Act: -0.1700
Data Index: 6077712 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.3374. Min Act: -0.1700
Data Index: 573790 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.3688. Min Act: -0.1700
Data Index: 574934 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.3531. Min Act: -0.1700
Data Index: 1656420 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.3374. Min Act: -0.1700
Data Index: 2082133 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4785. Min Range: -3.4785
Max Act: 3.3531. Min Act: -0.1700
Data Index: 953908 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19