Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4200 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.5317. Min Act: -0.1700
Data Index: 8363459 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.2505. Min Act: -0.1700
Data Index: 7100505 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0942. Min Act: -0.1700
Data Index: 360294 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0942. Min Act: -0.1700
Data Index: 2109977 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0630. Min Act: -0.1700
Data Index: 8824874 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0630. Min Act: -0.1700
Data Index: 7065250 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5317. Min Range: -7.5317
Max Act: 7.0005. Min Act: -0.1700
Data Index: 6592755 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9380. Min Act: -0.1700
Data Index: 491505 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9692. Min Act: -0.1700
Data Index: 4003968 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9380. Min Act: -0.1700
Data Index: 8086166 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9380. Min Act: -0.1700
Data Index: 7299831 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9067. Min Act: -0.1700
Data Index: 6477889 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.9067. Min Act: -0.1700
Data Index: 4655102 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8755. Min Act: -0.1700
Data Index: 293713 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8755. Min Act: -0.1700
Data Index: 4867071 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8442. Min Act: -0.1700
Data Index: 6141784 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8130. Min Act: -0.1700
Data Index: 2394975 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.8130. Min Act: -0.1700
Data Index: 222374 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.7817. Min Act: -0.1700
Data Index: 793525 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5317. Min Range: -7.5317
Max Act: 6.7817. Min Act: -0.1700
Data Index: 7205511 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19