Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 858 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.5172. Min Act: -0.1700
Data Index: 4576561 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.4235. Min Act: -0.1700
Data Index: 27164 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.3297. Min Act: -0.1700
Data Index: 6474473 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.2047. Min Act: -0.1700
Data Index: 2520222 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.2047. Min Act: -0.1700
Data Index: 3191972 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.2360. Min Act: -0.1700
Data Index: 1718596 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.2047. Min Act: -0.1700
Data Index: 327202 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.2047. Min Act: -0.1700
Data Index: 2083062 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.1735. Min Act: -0.1700
Data Index: 2942673 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.2047. Min Act: -0.1700
Data Index: 2032582 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.1735. Min Act: -0.1700
Data Index: 6224946 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.1110. Min Act: -0.1700
Data Index: 2908865 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.1110. Min Act: -0.1700
Data Index: 2406562 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.1110. Min Act: -0.1700
Data Index: 8252747 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.0797. Min Act: -0.1700
Data Index: 8716418 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.1110. Min Act: -0.1700
Data Index: 6057989 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.1110. Min Act: -0.1700
Data Index: 1149719 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.1110. Min Act: -0.1700
Data Index: 2984758 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.0797. Min Act: -0.1700
Data Index: 4874458 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5172. Min Range: -5.5172
Max Act: 5.0172. Min Act: -0.1700
Data Index: 6255550 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19