Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.5861. Min Act: -0.1700
Data Index: 8447875 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3986. Min Act: -0.1700
Data Index: 3128260 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3986. Min Act: -0.1700
Data Index: 5760472 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3361. Min Act: -0.1700
Data Index: 7801624 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3049. Min Act: -0.1700
Data Index: 3569165 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3674. Min Act: -0.1700
Data Index: 5262490 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3361. Min Act: -0.1700
Data Index: 6112561 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3361. Min Act: -0.1700
Data Index: 959932 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3049. Min Act: -0.1700
Data Index: 8345074 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2736. Min Act: -0.1700
Data Index: 1597442 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3049. Min Act: -0.1700
Data Index: 1470312 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2736. Min Act: -0.1700
Data Index: 3731994 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2424. Min Act: -0.1700
Data Index: 4283529 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2736. Min Act: -0.1700
Data Index: 7162411 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3049. Min Act: -0.1700
Data Index: 4824241 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2424. Min Act: -0.1700
Data Index: 5596785 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2111. Min Act: -0.1700
Data Index: 6977681 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2424. Min Act: -0.1700
Data Index: 3368103 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2111. Min Act: -0.1700
Data Index: 3009844 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2111. Min Act: -0.1700
Data Index: 5031417 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19