Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1728 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3925. Min Range: -4.3925
Max Act: 4.3925. Min Act: -0.1700
Data Index: 425656 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3925. Min Range: -4.3925
Max Act: 4.2050. Min Act: -0.1700
Data Index: 3006915 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3925. Min Range: -4.3925
Max Act: 4.1737. Min Act: -0.1700
Data Index: 3916161 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3925. Min Range: -4.3925
Max Act: 4.0799. Min Act: -0.1700
Data Index: 4276081 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3925. Min Range: -4.3925
Max Act: 4.0799. Min Act: -0.1700
Data Index: 2595565 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3925. Min Range: -4.3925
Max Act: 4.0799. Min Act: -0.1700
Data Index: 487672 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3925. Min Range: -4.3925
Max Act: 4.0174. Min Act: -0.1700
Data Index: 8411159 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3925. Min Range: -4.3925
Max Act: 4.0174. Min Act: -0.1700
Data Index: 5328290 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.9549. Min Act: -0.1700
Data Index: 2805936 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.9236. Min Act: -0.1700
Data Index: 6727671 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.9236. Min Act: -0.1700
Data Index: 2444278 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.9236. Min Act: -0.1700
Data Index: 3411554 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.9236. Min Act: -0.1700
Data Index: 2026410 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.9236. Min Act: -0.1700
Data Index: 1960050 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.8924. Min Act: -0.1700
Data Index: 2992089 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.8298. Min Act: -0.1700
Data Index: 2449967 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.8298. Min Act: -0.1700
Data Index: 255304 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.8298. Min Act: -0.1700
Data Index: 6242491 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.7986. Min Act: -0.1700
Data Index: 1480457 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3925. Min Range: -4.3925
Max Act: 3.8298. Min Act: -0.1700
Data Index: 8609985 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19