Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4491 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4642. Min Range: -9.4642
Max Act: 9.4642. Min Act: -0.1700
Data Index: 303279 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4642. Min Range: -9.4642
Max Act: 9.3392. Min Act: -0.1700
Data Index: 3322755 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4642. Min Range: -9.4642
Max Act: 9.1517. Min Act: -0.1700
Data Index: 4558393 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4642. Min Range: -9.4642
Max Act: 9.1517. Min Act: -0.1700
Data Index: 5979106 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4642. Min Range: -9.4642
Max Act: 9.1517. Min Act: -0.1700
Data Index: 4457981 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4642. Min Range: -9.4642
Max Act: 9.0267. Min Act: -0.1700
Data Index: 2098530 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.9017. Min Act: -0.1700
Data Index: 1330138 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.8392. Min Act: -0.1700
Data Index: 682823 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.8392. Min Act: -0.1700
Data Index: 8202845 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.8392. Min Act: -0.1700
Data Index: 2850040 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.7767. Min Act: -0.1700
Data Index: 3572834 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.7767. Min Act: -0.1700
Data Index: 246873 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.7142. Min Act: -0.1700
Data Index: 2760182 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.7142. Min Act: -0.1700
Data Index: 4726797 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.7767. Min Act: -0.1700
Data Index: 6866734 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.6517. Min Act: -0.1700
Data Index: 6884030 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.7142. Min Act: -0.1700
Data Index: 94206 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.6517. Min Act: -0.1700
Data Index: 1924407 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.6517. Min Act: -0.1700
Data Index: 1234324 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4642. Min Range: -9.4642
Max Act: 8.5892. Min Act: -0.1700
Data Index: 2696336 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19