Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.3206. Min Act: -0.1700
Data Index: 159673 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.1477. Min Act: -0.1700
Data Index: 2654572 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.0847. Min Act: -0.1700
Data Index: 2869194 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.0532. Min Act: -0.1700
Data Index: 673773 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.0374. Min Act: -0.1700
Data Index: 1548395 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.0374. Min Act: -0.1700
Data Index: 3223220 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.0374. Min Act: -0.1700
Data Index: 2912083 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3206. Min Range: -3.3206
Max Act: 3.0058. Min Act: -0.1700
Data Index: 1986245 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9742. Min Act: -0.1700
Data Index: 7258698 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9900. Min Act: -0.1700
Data Index: 4740453 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9900. Min Act: -0.1700
Data Index: 8399544 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9742. Min Act: -0.1700
Data Index: 2228756 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9584. Min Act: -0.1700
Data Index: 290237 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9742. Min Act: -0.1700
Data Index: 4249037 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9742. Min Act: -0.1700
Data Index: 5887961 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9900. Min Act: -0.1700
Data Index: 6697950 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9584. Min Act: -0.1700
Data Index: 5137659 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9584. Min Act: -0.1700
Data Index: 6704784 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9742. Min Act: -0.1700
Data Index: 7594990 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3206. Min Range: -3.3206
Max Act: 2.9584. Min Act: -0.1700
Data Index: 659818 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19