Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1598 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0259. Min Range: -3.0259
Max Act: 3.0259. Min Act: -0.1700
Data Index: 3513139 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0259. Min Range: -3.0259
Max Act: 3.0101. Min Act: -0.1700
Data Index: 491442 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0259. Min Range: -3.0259
Max Act: 3.0259. Min Act: -0.1605
Data Index: 496596 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0259. Min Range: -3.0259
Max Act: 3.0259. Min Act: -0.1693
Data Index: 4511292 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.9784. Min Act: -0.1692
Data Index: 1564994 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.9310. Min Act: -0.1700
Data Index: 4619453 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.9151. Min Act: -0.1688
Data Index: 1587844 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8993. Min Act: -0.1700
Data Index: 6712829 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8993. Min Act: -0.1700
Data Index: 6586838 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8675. Min Act: -0.1700
Data Index: 1068933 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8834. Min Act: -0.1700
Data Index: 154123 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8357. Min Act: -0.1699
Data Index: 1023939 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8675. Min Act: -0.1700
Data Index: 7443529 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8675. Min Act: -0.1561
Data Index: 492915 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8675. Min Act: -0.1696
Data Index: 6888309 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8993. Min Act: -0.1700
Data Index: 4274972 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8675. Min Act: -0.1700
Data Index: 6830699 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8834. Min Act: -0.1700
Data Index: 2620958 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8516. Min Act: -0.1700
Data Index: 838064 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0259. Min Range: -3.0259
Max Act: 2.8357. Min Act: -0.1700
Data Index: 7053747 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19