Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1327 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.7700. Min Act: -0.1700
Data Index: 6074561 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.4575. Min Act: -0.1700
Data Index: 1370647 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.4575. Min Act: -0.1700
Data Index: 1878630 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.3325. Min Act: -0.1700
Data Index: 1231748 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.3325. Min Act: -0.1700
Data Index: 4815375 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.2700. Min Act: -0.1700
Data Index: 5888148 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.2388. Min Act: -0.1700
Data Index: 1063880 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.2075. Min Act: -0.1700
Data Index: 6484821 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.2700. Min Act: -0.1700
Data Index: 4071991 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.1763. Min Act: -0.1700
Data Index: 4317487 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.1763. Min Act: -0.1700
Data Index: 2376108 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.1763. Min Act: -0.1700
Data Index: 2584136 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.1763. Min Act: -0.1700
Data Index: 4325881 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.1450. Min Act: -0.1700
Data Index: 4547602 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.1450. Min Act: -0.1700
Data Index: 8652903 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.1138. Min Act: -0.1700
Data Index: 395161 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.1138. Min Act: -0.1700
Data Index: 1028780 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.0825. Min Act: -0.1700
Data Index: 3046274 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7700. Min Range: -6.7700
Max Act: 6.0513. Min Act: -0.1700
Data Index: 336446 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7700. Min Range: -6.7700
Max Act: 5.9888. Min Act: -0.1700
Data Index: 662198 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19