Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4343 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0787. Min Range: -2.0787
Max Act: 2.0787. Min Act: -0.1700
Data Index: 8342181 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0787. Min Range: -2.0787
Max Act: 2.0451. Min Act: -0.1700
Data Index: 4993229 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0787. Min Range: -2.0787
Max Act: 2.0283. Min Act: -0.1700
Data Index: 5126204 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0787. Min Range: -2.0787
Max Act: 2.0114. Min Act: -0.1700
Data Index: 1218907 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9945. Min Act: -0.1700
Data Index: 4383681 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9606. Min Act: -0.1700
Data Index: 8803720 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9606. Min Act: -0.1700
Data Index: 7994871 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9266. Min Act: -0.1700
Data Index: 4572979 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9436. Min Act: -0.1700
Data Index: 1852375 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9436. Min Act: -0.1700
Data Index: 2751878 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9436. Min Act: -0.1699
Data Index: 1363168 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9436. Min Act: -0.1700
Data Index: 4282694 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9266. Min Act: -0.1700
Data Index: 4487194 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9266. Min Act: -0.1700
Data Index: 5485055 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9436. Min Act: -0.1700
Data Index: 4993230 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9436. Min Act: -0.1700
Data Index: 2251613 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9096. Min Act: -0.1700
Data Index: 1673895 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9096. Min Act: -0.1700
Data Index: 8551706 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9266. Min Act: -0.1700
Data Index: 3722742 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0787. Min Range: -2.0787
Max Act: 1.9266. Min Act: -0.1700
Data Index: 1761816 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19