Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0400. Min Range: -7.0400
Max Act: 7.0400. Min Act: -0.1700
Data Index: 1879718 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.9463. Min Act: -0.1700
Data Index: 8764196 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.6650. Min Act: -0.1700
Data Index: 1879720 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.6338. Min Act: -0.1700
Data Index: 2171280 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.5713. Min Act: -0.1700
Data Index: 6783576 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.5088. Min Act: -0.1700
Data Index: 2590916 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.4463. Min Act: -0.1700
Data Index: 152334 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.4150. Min Act: -0.1700
Data Index: 202085 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.3838. Min Act: -0.1700
Data Index: 3286467 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.3213. Min Act: -0.1700
Data Index: 1100223 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.2900. Min Act: -0.1700
Data Index: 2107174 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.2588. Min Act: -0.1700
Data Index: 1253452 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.2275. Min Act: -0.1700
Data Index: 3791241 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.1963. Min Act: -0.1700
Data Index: 8620299 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.1963. Min Act: -0.1700
Data Index: 644664 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.1963. Min Act: -0.1700
Data Index: 7588132 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.1650. Min Act: -0.1700
Data Index: 1235449 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.1650. Min Act: -0.1700
Data Index: 6921218 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.1338. Min Act: -0.1700
Data Index: 8463481 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0400. Min Range: -7.0400
Max Act: 6.1025. Min Act: -0.1700
Data Index: 4537861 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19