Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5288 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4909. Min Range: -6.4909
Max Act: 6.4909. Min Act: -0.1700
Data Index: 7244232 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4909. Min Range: -6.4909
Max Act: 6.2096. Min Act: -0.1700
Data Index: 5857309 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4909. Min Range: -6.4909
Max Act: 6.1784. Min Act: -0.1700
Data Index: 8477558 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4909. Min Range: -6.4909
Max Act: 6.0846. Min Act: -0.1700
Data Index: 4059549 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.9596. Min Act: -0.1700
Data Index: 4913034 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.9284. Min Act: -0.1700
Data Index: 5992538 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.8971. Min Act: -0.1700
Data Index: 5318226 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.8971. Min Act: -0.1700
Data Index: 5256151 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.8659. Min Act: -0.1700
Data Index: 1525260 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.8971. Min Act: -0.1700
Data Index: 6415044 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.8346. Min Act: -0.1700
Data Index: 703895 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.8034. Min Act: -0.1700
Data Index: 2019198 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.7721. Min Act: -0.1700
Data Index: 7051189 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.7721. Min Act: -0.1700
Data Index: 6649316 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.7409. Min Act: -0.1700
Data Index: 5096937 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.6784. Min Act: -0.1700
Data Index: 554424 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.7096. Min Act: -0.1700
Data Index: 1571831 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.7096. Min Act: -0.1700
Data Index: 4648577 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.6784. Min Act: -0.1700
Data Index: 416045 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4909. Min Range: -6.4909
Max Act: 5.6784. Min Act: -0.1700
Data Index: 1988884 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19