Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2602 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4694. Min Range: -5.4694
Max Act: 5.4694. Min Act: -0.1700
Data Index: 7191616 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4694. Min Range: -5.4694
Max Act: 5.2194. Min Act: -0.1700
Data Index: 7749139 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4694. Min Range: -5.4694
Max Act: 5.1569. Min Act: -0.1700
Data Index: 3380401 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4694. Min Range: -5.4694
Max Act: 5.0944. Min Act: -0.1700
Data Index: 1946685 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4694. Min Range: -5.4694
Max Act: 5.0006. Min Act: -0.1700
Data Index: 7387327 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.9381. Min Act: -0.1700
Data Index: 937829 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.9694. Min Act: -0.1700
Data Index: 1255972 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.9381. Min Act: -0.1700
Data Index: 5619256 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.9069. Min Act: -0.1700
Data Index: 5070815 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.9069. Min Act: -0.1700
Data Index: 6753069 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8444. Min Act: -0.1700
Data Index: 3557731 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8444. Min Act: -0.1700
Data Index: 5256099 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8444. Min Act: -0.1700
Data Index: 8764127 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8444. Min Act: -0.1700
Data Index: 1292516 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8131. Min Act: -0.1700
Data Index: 8570431 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8131. Min Act: -0.1700
Data Index: 2609463 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8444. Min Act: -0.1700
Data Index: 8101355 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8444. Min Act: -0.1700
Data Index: 400932 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8444. Min Act: -0.1700
Data Index: 7600311 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4694. Min Range: -5.4694
Max Act: 4.8131. Min Act: -0.1700
Data Index: 4667197 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19