Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1947 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.2983. Min Range: -6.2983
Max Act: 6.2671. Min Act: -0.1700
Data Index: 7589894 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2983. Min Range: -6.2983
Max Act: 6.2983. Min Act: -0.1700
Data Index: 7110841 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2983. Min Range: -6.2983
Max Act: 6.2671. Min Act: -0.1700
Data Index: 932382 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2983. Min Range: -6.2983
Max Act: 6.1733. Min Act: -0.1700
Data Index: 5107892 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2983. Min Range: -6.2983
Max Act: 6.1108. Min Act: -0.1700
Data Index: 6609276 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2983. Min Range: -6.2983
Max Act: 6.0796. Min Act: -0.1700
Data Index: 650108 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2983. Min Range: -6.2983
Max Act: 6.0171. Min Act: -0.1700
Data Index: 5620997 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2983. Min Range: -6.2983
Max Act: 6.0483. Min Act: -0.1700
Data Index: 5973370 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.9546. Min Act: -0.1700
Data Index: 5296686 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.9858. Min Act: -0.1700
Data Index: 7418754 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.9546. Min Act: -0.1700
Data Index: 3162339 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.9233. Min Act: -0.1700
Data Index: 4244995 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.9233. Min Act: -0.1700
Data Index: 4132174 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.9546. Min Act: -0.1700
Data Index: 1626160 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.8921. Min Act: -0.1700
Data Index: 5370167 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.8921. Min Act: -0.1700
Data Index: 1478895 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.8921. Min Act: -0.1700
Data Index: 5756729 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.8608. Min Act: -0.1700
Data Index: 7137307 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.8608. Min Act: -0.1700
Data Index: 4036357 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2983. Min Range: -6.2983
Max Act: 5.8921. Min Act: -0.1700
Data Index: 4059968 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19