Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3846 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.4685. Min Act: -0.1700
Data Index: 4828095 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.2185. Min Act: -0.1700
Data Index: 4619070 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.1872. Min Act: -0.1700
Data Index: 3011385 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.1560. Min Act: -0.1700
Data Index: 5483627 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.1247. Min Act: -0.1700
Data Index: 5340640 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.1247. Min Act: -0.1700
Data Index: 1592447 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.0310. Min Act: -0.1700
Data Index: 6723233 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4685. Min Range: -6.4685
Max Act: 6.0310. Min Act: -0.1700
Data Index: 976552 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9685. Min Act: -0.1700
Data Index: 5757905 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9372. Min Act: -0.1700
Data Index: 5491096 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9060. Min Act: -0.1700
Data Index: 1293848 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9060. Min Act: -0.1700
Data Index: 6656146 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9060. Min Act: -0.1700
Data Index: 5439919 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.9060. Min Act: -0.1700
Data Index: 3881367 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8747. Min Act: -0.1700
Data Index: 4454440 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8435. Min Act: -0.1700
Data Index: 4765038 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8747. Min Act: -0.1700
Data Index: 1498609 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8122. Min Act: -0.1700
Data Index: 735006 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8435. Min Act: -0.1700
Data Index: 2280699 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4685. Min Range: -6.4685
Max Act: 5.8435. Min Act: -0.1700
Data Index: 5152751 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19