Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4935 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.4647. Min Act: -0.1700
Data Index: 6149967 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.2772. Min Act: -0.1700
Data Index: 8366696 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.1210. Min Act: -0.1700
Data Index: 8439246 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.1210. Min Act: -0.1700
Data Index: 7477939 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.0897. Min Act: -0.1700
Data Index: 1375997 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.0584. Min Act: -0.1700
Data Index: 330768 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.0584. Min Act: -0.1700
Data Index: 4669145 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.0584. Min Act: -0.1700
Data Index: 6476462 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.0272. Min Act: -0.1700
Data Index: 911210 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.0272. Min Act: -0.1700
Data Index: 2934134 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4647. Min Range: -4.4647
Max Act: 4.0272. Min Act: -0.1700
Data Index: 907718 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4647. Min Range: -4.4647
Max Act: 3.9959. Min Act: -0.1700
Data Index: 8129489 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4647. Min Range: -4.4647
Max Act: 3.9647. Min Act: -0.1700
Data Index: 2357938 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4647. Min Range: -4.4647
Max Act: 3.9647. Min Act: -0.1700
Data Index: 6521059 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4647. Min Range: -4.4647
Max Act: 3.9647. Min Act: -0.1700
Data Index: 2205111 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4647. Min Range: -4.4647
Max Act: 3.9647. Min Act: -0.1700
Data Index: 1448661 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4647. Min Range: -4.4647
Max Act: 3.9647. Min Act: -0.1700
Data Index: 8512560 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4647. Min Range: -4.4647
Max Act: 3.9647. Min Act: -0.1700
Data Index: 4340682 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4647. Min Range: -4.4647
Max Act: 3.9334. Min Act: -0.1700
Data Index: 8342781 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4647. Min Range: -4.4647
Max Act: 3.9334. Min Act: -0.1700
Data Index: 755210 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19