Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.8169. Min Act: -0.1700
Data Index: 701459 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.6919. Min Act: -0.1700
Data Index: 701455 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.6294. Min Act: -0.1700
Data Index: 701457 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.6294. Min Act: -0.1700
Data Index: 701462 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.5669. Min Act: -0.1700
Data Index: 701474 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.5357. Min Act: -0.1700
Data Index: 7241801 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.5669. Min Act: -0.1700
Data Index: 701481 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.5357. Min Act: -0.1700
Data Index: 7574862 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.5357. Min Act: -0.1700
Data Index: 701469 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.4732. Min Act: -0.1700
Data Index: 701485 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.4732. Min Act: -0.1700
Data Index: 3706198 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.4732. Min Act: -0.1700
Data Index: 7260155 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.4419. Min Act: -0.1700
Data Index: 3132310 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.4419. Min Act: -0.1700
Data Index: 701475 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.4419. Min Act: -0.1700
Data Index: 7374339 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.3794. Min Act: -0.1700
Data Index: 6024440 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.4106. Min Act: -0.1700
Data Index: 701456 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.4106. Min Act: -0.1700
Data Index: 701476 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.3794. Min Act: -0.1700
Data Index: 1020149 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8169. Min Range: -4.8169
Max Act: 4.3481. Min Act: -0.1700
Data Index: 6931766 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19