Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1283 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 15.2811. Min Range: -15.2811
Max Act: 15.2811. Min Act: -0.1700
Data Index: 1585111 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.2811. Min Range: -15.2811
Max Act: 15.1561. Min Act: -0.1700
Data Index: 5451964 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.2811. Min Range: -15.2811
Max Act: 15.0936. Min Act: -0.1700
Data Index: 5640055 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.5936. Min Act: -0.1700
Data Index: 2372176 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.5311. Min Act: -0.1700
Data Index: 1179734 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.4686. Min Act: -0.1700
Data Index: 5996707 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.5311. Min Act: -0.1700
Data Index: 8291543 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.5311. Min Act: -0.1700
Data Index: 877872 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.5311. Min Act: -0.1700
Data Index: 4335960 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.4686. Min Act: -0.1700
Data Index: 5295790 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.4061. Min Act: -0.1700
Data Index: 3601989 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.3436. Min Act: -0.1700
Data Index: 5724236 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.3436. Min Act: -0.1700
Data Index: 5130460 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.2811. Min Act: -0.1700
Data Index: 693902 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.2811. Min Act: -0.1700
Data Index: 2635832 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.2811. Min Act: -0.1700
Data Index: 5726512 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.1561. Min Act: -0.1700
Data Index: 4380037 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.1561. Min Act: -0.1700
Data Index: 388842 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.2186. Min Act: -0.1700
Data Index: 2287411 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.2811. Min Range: -15.2811
Max Act: 14.0311. Min Act: -0.1700
Data Index: 931249 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19