Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1172. Min Range: -5.1172
Max Act: 5.1172. Min Act: -0.1700
Data Index: 4963234 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.9922. Min Act: -0.1700
Data Index: 6796570 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.8985. Min Act: -0.1700
Data Index: 3895083 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.8672. Min Act: -0.1700
Data Index: 4674150 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.8360. Min Act: -0.1700
Data Index: 5141914 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.8047. Min Act: -0.1700
Data Index: 309774 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.8047. Min Act: -0.1700
Data Index: 473833 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.8047. Min Act: -0.1700
Data Index: 4270705 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.8047. Min Act: -0.1700
Data Index: 1452422 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7735. Min Act: -0.1700
Data Index: 2102357 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7735. Min Act: -0.1700
Data Index: 4402851 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7735. Min Act: -0.1700
Data Index: 1926350 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7735. Min Act: -0.1700
Data Index: 3351758 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7422. Min Act: -0.1700
Data Index: 4967332 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7422. Min Act: -0.1700
Data Index: 4674151 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7422. Min Act: -0.1700
Data Index: 6276337 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7110. Min Act: -0.1700
Data Index: 1153268 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7422. Min Act: -0.1699
Data Index: 1289136 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7110. Min Act: -0.1700
Data Index: 1079370 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1172. Min Range: -5.1172
Max Act: 4.7422. Min Act: -0.1700
Data Index: 989787 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19