Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4426 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4484. Min Range: -7.4484
Max Act: 7.4484. Min Act: -0.1700
Data Index: 8153964 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4484. Min Range: -7.4484
Max Act: 7.3859. Min Act: -0.1700
Data Index: 303286 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4484. Min Range: -7.4484
Max Act: 7.1359. Min Act: -0.1700
Data Index: 1750709 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4484. Min Range: -7.4484
Max Act: 7.0421. Min Act: -0.1700
Data Index: 720903 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4484. Min Range: -7.4484
Max Act: 7.0421. Min Act: -0.1700
Data Index: 453706 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.9484. Min Act: -0.1700
Data Index: 6940694 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.9484. Min Act: -0.1700
Data Index: 5914094 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.9484. Min Act: -0.1700
Data Index: 3337512 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.9484. Min Act: -0.1700
Data Index: 4134441 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.9484. Min Act: -0.1700
Data Index: 8677489 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.9171. Min Act: -0.1700
Data Index: 7825462 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.9171. Min Act: -0.1700
Data Index: 5937261 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.9171. Min Act: -0.1700
Data Index: 2196207 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.9171. Min Act: -0.1700
Data Index: 3230834 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.8859. Min Act: -0.1700
Data Index: 8376887 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.8546. Min Act: -0.1700
Data Index: 328864 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.8234. Min Act: -0.1700
Data Index: 4052547 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.8546. Min Act: -0.1700
Data Index: 3408821 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.8546. Min Act: -0.1700
Data Index: 7625828 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4484. Min Range: -7.4484
Max Act: 6.8546. Min Act: -0.1700
Data Index: 8680157 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19