Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3839 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.6467. Min Act: -0.1700
Data Index: 205092 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.5663. Min Act: -0.1700
Data Index: 8357292 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.5178. Min Act: -0.1700
Data Index: 3253161 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.5016. Min Act: -0.1700
Data Index: 4441774 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.5016. Min Act: -0.1700
Data Index: 4377900 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.5016. Min Act: -0.1700
Data Index: 6835877 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.5178. Min Act: -0.1700
Data Index: 7312772 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.5340. Min Act: -0.1700
Data Index: 4692048 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.5016. Min Act: -0.1700
Data Index: 7453580 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.5016. Min Act: -0.1700
Data Index: 2185000 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4692. Min Act: -0.1700
Data Index: 7485659 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4692. Min Act: -0.1700
Data Index: 4207829 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4529. Min Act: -0.1700
Data Index: 4206303 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4854. Min Act: -0.1700
Data Index: 6207782 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4529. Min Act: -0.1700
Data Index: 3564767 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4367. Min Act: -0.1700
Data Index: 870790 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4529. Min Act: -0.1700
Data Index: 2522119 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4529. Min Act: -0.1700
Data Index: 2137015 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4367. Min Act: -0.1700
Data Index: 4884399 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6467. Min Range: -2.6467
Max Act: 2.4367. Min Act: -0.1700
Data Index: 4792980 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19