Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2854 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.7124. Min Act: -0.1700
Data Index: 347204 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.7280. Min Act: -0.1700
Data Index: 5050803 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.7124. Min Act: -0.1700
Data Index: 8618493 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6968. Min Act: -0.1700
Data Index: 105819 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.7124. Min Act: -0.1700
Data Index: 7416787 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6498. Min Act: -0.1700
Data Index: 6531152 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6342. Min Act: -0.1700
Data Index: 4877372 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6185. Min Act: -0.1700
Data Index: 5032676 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6342. Min Act: -0.1700
Data Index: 414059 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6185. Min Act: -0.1700
Data Index: 2406196 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6185. Min Act: -0.1700
Data Index: 5158905 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6029. Min Act: -0.1700
Data Index: 7363463 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6029. Min Act: -0.1700
Data Index: 6117476 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.5716. Min Act: -0.1700
Data Index: 5052257 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.5716. Min Act: -0.1700
Data Index: 7732986 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.6029. Min Act: -0.1700
Data Index: 3586302 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.5872. Min Act: -0.1700
Data Index: 6726881 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.5559. Min Act: -0.1700
Data Index: 8597817 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.5403. Min Act: -0.1700
Data Index: 4570814 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7280. Min Range: -3.7280
Max Act: 3.5716. Min Act: -0.1700
Data Index: 5671162 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19