Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5663 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.5214. Min Act: -0.1700
Data Index: 5616098 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.4902. Min Act: -0.1700
Data Index: 2194129 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.4277. Min Act: -0.1700
Data Index: 3106321 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3339. Min Act: -0.1700
Data Index: 8752977 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.2714. Min Act: -0.1700
Data Index: 8708029 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3027. Min Act: -0.1700
Data Index: 6182394 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3027. Min Act: -0.1700
Data Index: 5604848 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.2402. Min Act: -0.1700
Data Index: 371308 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.2089. Min Act: -0.1700
Data Index: 5960175 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.1777. Min Act: -0.1700
Data Index: 5787741 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.1777. Min Act: -0.1700
Data Index: 1033843 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.1777. Min Act: -0.1700
Data Index: 8278381 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.1152. Min Act: -0.1700
Data Index: 8362186 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.1152. Min Act: -0.1700
Data Index: 3552095 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.1152. Min Act: -0.1700
Data Index: 5315752 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.1152. Min Act: -0.1700
Data Index: 5872626 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.0527. Min Act: -0.1700
Data Index: 1202090 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.0839. Min Act: -0.1700
Data Index: 8207648 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.0839. Min Act: -0.1700
Data Index: 561385 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.1152. Min Act: -0.1700
Data Index: 6880757 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19