Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 590 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1184. Min Range: -7.1184
Max Act: 7.1184. Min Act: -0.1700
Data Index: 1447532 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.9934. Min Act: -0.1700
Data Index: 8334120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.9309. Min Act: -0.1700
Data Index: 2538995 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8059. Min Act: -0.1700
Data Index: 1757125 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8684. Min Act: -0.1700
Data Index: 5416880 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8059. Min Act: -0.1700
Data Index: 5672330 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8059. Min Act: -0.1700
Data Index: 6091304 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.8059. Min Act: -0.1700
Data Index: 8381773 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.7746. Min Act: -0.1700
Data Index: 4223859 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.7121. Min Act: -0.1700
Data Index: 2958155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6496. Min Act: -0.1700
Data Index: 2620277 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6184. Min Act: -0.1700
Data Index: 8606347 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6496. Min Act: -0.1700
Data Index: 6358479 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6496. Min Act: -0.1700
Data Index: 263261 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6184. Min Act: -0.1700
Data Index: 840856 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6496. Min Act: -0.1700
Data Index: 317018 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6184. Min Act: -0.1700
Data Index: 2735685 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.6184. Min Act: -0.1700
Data Index: 617649 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.5871. Min Act: -0.1700
Data Index: 6682092 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1184. Min Range: -7.1184
Max Act: 6.5559. Min Act: -0.1700
Data Index: 5616753 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19