Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3249 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.4592. Min Act: -0.1700
Data Index: 7665821 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.3655. Min Act: -0.1700
Data Index: 6385849 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.3030. Min Act: -0.1700
Data Index: 8016582 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.2717. Min Act: -0.1700
Data Index: 4358428 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.2717. Min Act: -0.1700
Data Index: 2246411 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.2405. Min Act: -0.1700
Data Index: 880598 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.2405. Min Act: -0.1700
Data Index: 1139015 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.2405. Min Act: -0.1700
Data Index: 6748011 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.2092. Min Act: -0.1700
Data Index: 7214976 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.2092. Min Act: -0.1700
Data Index: 4654898 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.2092. Min Act: -0.1700
Data Index: 4358429 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.2092. Min Act: -0.1700
Data Index: 5267391 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.1780. Min Act: -0.1700
Data Index: 5878053 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.1467. Min Act: -0.1700
Data Index: 1376687 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.1467. Min Act: -0.1700
Data Index: 459271 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.1155. Min Act: -0.1700
Data Index: 3480815 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.1155. Min Act: -0.1700
Data Index: 2919208 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.1155. Min Act: -0.1700
Data Index: 219439 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.0842. Min Act: -0.1700
Data Index: 219437 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4592. Min Range: -7.4592
Max Act: 7.0842. Min Act: -0.1700
Data Index: 5125977 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19