Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 825 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.2107. Min Act: -0.1700
Data Index: 5501610 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1775. Min Act: -0.1700
Data Index: 8084334 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1775. Min Act: -0.1700
Data Index: 102815 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1941. Min Act: -0.1700
Data Index: 3424772 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1775. Min Act: -0.1700
Data Index: 6931240 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1609. Min Act: -0.1700
Data Index: 120725 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1609. Min Act: -0.1700
Data Index: 4175751 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1442. Min Act: -0.1700
Data Index: 3420461 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1609. Min Act: -0.1700
Data Index: 6416930 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1442. Min Act: -0.1700
Data Index: 5725122 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1609. Min Act: -0.1700
Data Index: 6495474 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1609. Min Act: -0.1700
Data Index: 211058 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1442. Min Act: -0.1700
Data Index: 5643875 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1275. Min Act: -0.1699
Data Index: 8765255 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1275. Min Act: -0.1700
Data Index: 5900479 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1108. Min Act: -0.1700
Data Index: 710779 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1275. Min Act: -0.1700
Data Index: 1174437 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1108. Min Act: -0.1700
Data Index: 4739750 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1108. Min Act: -0.1697
Data Index: 3172466 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2107. Min Range: -2.2107
Max Act: 2.1108. Min Act: -0.1700
Data Index: 895027 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19