Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.8839. Min Act: -0.1700
Data Index: 3968119 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.8527. Min Act: -0.1700
Data Index: 8506631 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.8527. Min Act: -0.1700
Data Index: 1369983 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.8214. Min Act: -0.1700
Data Index: 808087 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.7902. Min Act: -0.1700
Data Index: 8459930 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.7277. Min Act: -0.1700
Data Index: 4543602 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.7277. Min Act: -0.1700
Data Index: 554323 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6964. Min Act: -0.1700
Data Index: 4378993 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6652. Min Act: -0.1700
Data Index: 1514644 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6964. Min Act: -0.1700
Data Index: 8352807 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6964. Min Act: -0.1700
Data Index: 4411100 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6339. Min Act: -0.1700
Data Index: 139640 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6027. Min Act: -0.1700
Data Index: 4504895 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6339. Min Act: -0.1700
Data Index: 6181646 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6027. Min Act: -0.1700
Data Index: 925757 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6027. Min Act: -0.1700
Data Index: 129268 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.6339. Min Act: -0.1700
Data Index: 7915231 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.5714. Min Act: -0.1700
Data Index: 318222 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.5714. Min Act: -0.1700
Data Index: 8455519 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8839. Min Range: -6.8839
Max Act: 6.5402. Min Act: -0.1700
Data Index: 5857044 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19