Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4659 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0494. Min Range: -5.0494
Max Act: 5.0494. Min Act: -0.1700
Data Index: 6838145 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.8619. Min Act: -0.1700
Data Index: 8324787 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.7682. Min Act: -0.1700
Data Index: 6897674 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.7994. Min Act: -0.1700
Data Index: 4300317 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.7682. Min Act: -0.1700
Data Index: 5679934 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.7369. Min Act: -0.1700
Data Index: 7699511 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.7369. Min Act: -0.1700
Data Index: 4228304 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6744. Min Act: -0.1700
Data Index: 5400600 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6744. Min Act: -0.1700
Data Index: 6624598 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6432. Min Act: -0.1700
Data Index: 3427234 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6744. Min Act: -0.1700
Data Index: 7131228 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6119. Min Act: -0.1700
Data Index: 6775977 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6432. Min Act: -0.1700
Data Index: 348623 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6744. Min Act: -0.1700
Data Index: 2465148 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6119. Min Act: -0.1700
Data Index: 1582106 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6119. Min Act: -0.1700
Data Index: 3947782 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.5807. Min Act: -0.1700
Data Index: 1718831 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6119. Min Act: -0.1700
Data Index: 5279599 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6432. Min Act: -0.1700
Data Index: 6746024 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0494. Min Range: -5.0494
Max Act: 4.6119. Min Act: -0.1700
Data Index: 27133 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19