Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1550 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7660. Min Range: -9.7660
Max Act: 9.7660. Min Act: -0.1700
Data Index: 3372075 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7660. Min Range: -9.7660
Max Act: 9.5160. Min Act: -0.1700
Data Index: 4316564 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7660. Min Range: -9.7660
Max Act: 9.4535. Min Act: -0.1700
Data Index: 1125667 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7660. Min Range: -9.7660
Max Act: 9.4535. Min Act: -0.1700
Data Index: 4543753 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7660. Min Range: -9.7660
Max Act: 9.4535. Min Act: -0.1700
Data Index: 1078424 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7660. Min Range: -9.7660
Max Act: 9.2035. Min Act: -0.1700
Data Index: 3985209 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7660. Min Range: -9.7660
Max Act: 9.1410. Min Act: -0.1700
Data Index: 8782168 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7660. Min Range: -9.7660
Max Act: 9.1410. Min Act: -0.1700
Data Index: 7877343 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7660. Min Range: -9.7660
Max Act: 9.0785. Min Act: -0.1700
Data Index: 6201081 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.9535. Min Act: -0.1700
Data Index: 4164080 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.8910. Min Act: -0.1700
Data Index: 7722691 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.8910. Min Act: -0.1700
Data Index: 8287273 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.8285. Min Act: -0.1700
Data Index: 5344228 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.8285. Min Act: -0.1700
Data Index: 204600 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.8285. Min Act: -0.1700
Data Index: 104213 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.8285. Min Act: -0.1700
Data Index: 4854168 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.7660. Min Act: -0.1700
Data Index: 2073188 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.7660. Min Act: -0.1700
Data Index: 3778382 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.7660. Min Act: -0.1700
Data Index: 2573322 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7660. Min Range: -9.7660
Max Act: 8.7660. Min Act: -0.1700
Data Index: 6942707 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19