Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.7183. Min Act: -0.1700
Data Index: 4383655 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.6871. Min Act: -0.1700
Data Index: 4612938 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.6558. Min Act: -0.1700
Data Index: 6540115 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.5621. Min Act: -0.1700
Data Index: 5935526 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4996. Min Act: -0.1700
Data Index: 7783694 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4996. Min Act: -0.1700
Data Index: 4731582 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4683. Min Act: -0.1700
Data Index: 765777 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4683. Min Act: -0.1700
Data Index: 7366989 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4371. Min Act: -0.1700
Data Index: 242368 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4371. Min Act: -0.1700
Data Index: 4488757 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4371. Min Act: -0.1700
Data Index: 8463266 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4058. Min Act: -0.1700
Data Index: 8053837 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4058. Min Act: -0.1700
Data Index: 1237172 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.4058. Min Act: -0.1700
Data Index: 4255692 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.3746. Min Act: -0.1700
Data Index: 2893958 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.3746. Min Act: -0.1700
Data Index: 4950350 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.3433. Min Act: -0.1700
Data Index: 8288261 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.3746. Min Act: -0.1700
Data Index: 3770717 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.3121. Min Act: -0.1700
Data Index: 3565016 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7183. Min Range: -5.7183
Max Act: 5.2808. Min Act: -0.1700
Data Index: 7774192 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19