Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2850 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1040. Min Range: -6.1040
Max Act: 6.1040. Min Act: -0.1700
Data Index: 6937409 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1040. Min Range: -6.1040
Max Act: 6.0102. Min Act: -0.1700
Data Index: 4876907 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.9165. Min Act: -0.1700
Data Index: 5232428 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.9477. Min Act: -0.1700
Data Index: 2640199 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.8227. Min Act: -0.1700
Data Index: 1600080 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.8227. Min Act: -0.1700
Data Index: 482850 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.8227. Min Act: -0.1700
Data Index: 756377 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7915. Min Act: -0.1700
Data Index: 5232427 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7915. Min Act: -0.1700
Data Index: 60987 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7915. Min Act: -0.1700
Data Index: 884487 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7915. Min Act: -0.1700
Data Index: 3773173 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7915. Min Act: -0.1700
Data Index: 6612895 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7915. Min Act: -0.1700
Data Index: 7677527 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7602. Min Act: -0.1700
Data Index: 318182 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7290. Min Act: -0.1700
Data Index: 2417644 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7602. Min Act: -0.1700
Data Index: 5675199 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7602. Min Act: -0.1700
Data Index: 8250490 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7602. Min Act: -0.1700
Data Index: 5003329 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7290. Min Act: -0.1700
Data Index: 6131009 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1040. Min Range: -6.1040
Max Act: 5.7290. Min Act: -0.1700
Data Index: 6485212 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19