Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2603 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.5154. Min Act: -0.1700
Data Index: 7958796 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.3904. Min Act: -0.1700
Data Index: 1194062 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.2029. Min Act: -0.1700
Data Index: 5062884 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.1716. Min Act: -0.1700
Data Index: 5406230 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.1716. Min Act: -0.1700
Data Index: 5951950 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.1091. Min Act: -0.1700
Data Index: 6943406 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.1404. Min Act: -0.1700
Data Index: 1822042 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.1404. Min Act: -0.1700
Data Index: 7270082 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.1404. Min Act: -0.1700
Data Index: 8376870 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.1404. Min Act: -0.1700
Data Index: 1920404 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.1091. Min Act: -0.1700
Data Index: 7140225 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.0466. Min Act: -0.1700
Data Index: 1368410 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.0466. Min Act: -0.1700
Data Index: 660713 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.0154. Min Act: -0.1700
Data Index: 2437196 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.0154. Min Act: -0.1700
Data Index: 6933278 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.0154. Min Act: -0.1700
Data Index: 4377247 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.0154. Min Act: -0.1700
Data Index: 6692303 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5154. Min Range: -5.5154
Max Act: 4.9841. Min Act: -0.1700
Data Index: 2897694 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5154. Min Range: -5.5154
Max Act: 4.9841. Min Act: -0.1700
Data Index: 3750739 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5154. Min Range: -5.5154
Max Act: 5.0154. Min Act: -0.1700
Data Index: 711856 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19