Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1283 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.8493. Min Act: -0.1700
Data Index: 5872574 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.5368. Min Act: -0.1700
Data Index: 878677 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.3493. Min Act: -0.1700
Data Index: 641233 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.3493. Min Act: -0.1700
Data Index: 2040606 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2555. Min Act: -0.1700
Data Index: 1200010 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2555. Min Act: -0.1700
Data Index: 2150870 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 5822540 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 79107 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2243. Min Act: -0.1700
Data Index: 3977267 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.1930. Min Act: -0.1700
Data Index: 7476084 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.2555. Min Act: -0.1700
Data Index: 5799047 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.1618. Min Act: -0.1700
Data Index: 3577396 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.1930. Min Act: -0.1700
Data Index: 5209422 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.1618. Min Act: -0.1700
Data Index: 2437969 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.1305. Min Act: -0.1700
Data Index: 5874338 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.0993. Min Act: -0.1700
Data Index: 5665077 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.0993. Min Act: -0.1700
Data Index: 6004008 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.0680. Min Act: -0.1700
Data Index: 4191183 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.0680. Min Act: -0.1700
Data Index: 3082079 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8493. Min Range: -6.8493
Max Act: 6.0680. Min Act: -0.1700
Data Index: 8009829 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19