Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3765 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2068. Min Range: -8.2068
Max Act: 8.2068. Min Act: -0.1700
Data Index: 3596648 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.4568. Min Act: -0.1700
Data Index: 5055154 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3943. Min Act: -0.1700
Data Index: 7819719 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3318. Min Act: -0.1700
Data Index: 2321976 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3318. Min Act: -0.1700
Data Index: 8819383 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.3630. Min Act: -0.1700
Data Index: 2321978 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.1755. Min Act: -0.1700
Data Index: 7044027 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.0505. Min Act: -0.1700
Data Index: 3849026 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.0193. Min Act: -0.1700
Data Index: 2596527 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2068. Min Range: -8.2068
Max Act: 7.0505. Min Act: -0.1700
Data Index: 7986516 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.9880. Min Act: -0.1700
Data Index: 3168330 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.9880. Min Act: -0.1700
Data Index: 942927 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.9880. Min Act: -0.1700
Data Index: 7986515 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.9568. Min Act: -0.1700
Data Index: 6282165 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.9568. Min Act: -0.1700
Data Index: 1698302 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.9568. Min Act: -0.1700
Data Index: 8170939 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.9880. Min Act: -0.1700
Data Index: 4185266 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.8630. Min Act: -0.1700
Data Index: 24902 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.9255. Min Act: -0.1700
Data Index: 2566693 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2068. Min Range: -8.2068
Max Act: 6.9568. Min Act: -0.1700
Data Index: 6559753 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19