Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4893 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.4148. Min Act: -0.1700
Data Index: 6688355 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3985. Min Act: -0.1700
Data Index: 267287 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3331. Min Act: -0.1700
Data Index: 2796408 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3331. Min Act: -0.1700
Data Index: 4485844 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3166. Min Act: -0.1699
Data Index: 6828886 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3331. Min Act: -0.1694
Data Index: 6828884 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3002. Min Act: -0.1700
Data Index: 3162183 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3002. Min Act: -0.1697
Data Index: 7708485 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3166. Min Act: -0.1692
Data Index: 6828888 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.3002. Min Act: -0.1699
Data Index: 3262658 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 3211532 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1695
Data Index: 7880448 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 4582967 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 5732236 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 3772909 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 6634263 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 8492831 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2673. Min Act: -0.1700
Data Index: 3460719 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2837. Min Act: -0.1700
Data Index: 2269334 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4148. Min Range: -2.4148
Max Act: 2.2673. Min Act: -0.1700
Data Index: 7408856 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19