Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 489 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.7543. Min Act: -0.1700
Data Index: 4333686 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.6135. Min Act: -0.1700
Data Index: 7852198 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.5822. Min Act: -0.1700
Data Index: 2742258 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.5196. Min Act: -0.1700
Data Index: 5564780 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.4883. Min Act: -0.1700
Data Index: 7166446 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.4099. Min Act: -0.1700
Data Index: 7689977 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3942. Min Act: -0.1700
Data Index: 8192309 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3785. Min Act: -0.1700
Data Index: 1042100 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3785. Min Act: -0.1700
Data Index: 2469347 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3629. Min Act: -0.1700
Data Index: 6732090 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3315. Min Act: -0.1700
Data Index: 3809863 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3785. Min Act: -0.1700
Data Index: 7284207 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3001. Min Act: -0.1700
Data Index: 7431708 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3315. Min Act: -0.1700
Data Index: 6659704 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3315. Min Act: -0.1700
Data Index: 6619659 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3315. Min Act: -0.1700
Data Index: 7210647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3315. Min Act: -0.1700
Data Index: 5630986 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3315. Min Act: -0.1700
Data Index: 6754332 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3315. Min Act: -0.1700
Data Index: 4027961 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7543. Min Range: -3.7543
Max Act: 3.3315. Min Act: -0.1700
Data Index: 6222168 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19