Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2520 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.9024. Min Act: -0.1700
Data Index: 1930650 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.8711. Min Act: -0.1700
Data Index: 952926 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.6836. Min Act: -0.1700
Data Index: 830200 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.6211. Min Act: -0.1700
Data Index: 4495885 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.5899. Min Act: -0.1700
Data Index: 5716984 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4961. Min Act: -0.1700
Data Index: 111068 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4961. Min Act: -0.1700
Data Index: 6740820 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4649. Min Act: -0.1700
Data Index: 4135020 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4961. Min Act: -0.1700
Data Index: 6635501 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4649. Min Act: -0.1700
Data Index: 3565863 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4961. Min Act: -0.1700
Data Index: 3757699 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4024. Min Act: -0.1700
Data Index: 1167326 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4336. Min Act: -0.1700
Data Index: 1093572 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4336. Min Act: -0.1700
Data Index: 6754940 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4336. Min Act: -0.1700
Data Index: 4535259 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4336. Min Act: -0.1700
Data Index: 3699863 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.4336. Min Act: -0.1700
Data Index: 4659947 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.3711. Min Act: -0.1700
Data Index: 6704895 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.3711. Min Act: -0.1700
Data Index: 3424704 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9024. Min Range: -5.9024
Max Act: 5.3711. Min Act: -0.1700
Data Index: 8642243 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19