Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5339 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.8738. Min Act: -0.1700
Data Index: 2101412 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.8738. Min Act: -0.1700
Data Index: 935018 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.8113. Min Act: -0.1700
Data Index: 4782276 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.6863. Min Act: -0.1700
Data Index: 7782861 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.7488. Min Act: -0.1700
Data Index: 935012 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.5613. Min Act: -0.1700
Data Index: 7281988 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.5613. Min Act: -0.1700
Data Index: 7220819 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.4988. Min Act: -0.1700
Data Index: 3430374 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.4988. Min Act: -0.1699
Data Index: 6406815 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.3738. Min Act: -0.1699
Data Index: 6719395 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.3113. Min Act: -0.1700
Data Index: 5369948 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.3113. Min Act: -0.1699
Data Index: 4664193 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.3113. Min Act: -0.1700
Data Index: 3379457 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.3113. Min Act: -0.1700
Data Index: 3700192 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.2488. Min Act: -0.1700
Data Index: 2613038 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.2176. Min Act: -0.1700
Data Index: 5614622 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.2176. Min Act: -0.1699
Data Index: 5277045 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.1238. Min Act: -0.1700
Data Index: 3904235 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.1238. Min Act: -0.1700
Data Index: 1234849 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8738. Min Range: -8.8738
Max Act: 8.1238. Min Act: -0.1700
Data Index: 5740236 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19