Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.8837. Min Act: -0.1700
Data Index: 5646759 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.6962. Min Act: -0.1700
Data Index: 655848 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.6650. Min Act: -0.1700
Data Index: 391511 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.6962. Min Act: -0.1700
Data Index: 4072391 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.5712. Min Act: -0.1700
Data Index: 3376964 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.4150. Min Act: -0.1700
Data Index: 1237520 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.4150. Min Act: -0.1700
Data Index: 1846980 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.3525. Min Act: -0.1700
Data Index: 3297381 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.2900. Min Act: -0.1700
Data Index: 3703131 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.2587. Min Act: -0.1700
Data Index: 4368085 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.2275. Min Act: -0.1700
Data Index: 2770666 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.1962. Min Act: -0.1700
Data Index: 4154368 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.1650. Min Act: -0.1700
Data Index: 7103615 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.1962. Min Act: -0.1700
Data Index: 4023735 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.1962. Min Act: -0.1700
Data Index: 5741469 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.1962. Min Act: -0.1700
Data Index: 3487457 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.1650. Min Act: -0.1700
Data Index: 7832591 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.1650. Min Act: -0.1700
Data Index: 7489908 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.1650. Min Act: -0.1700
Data Index: 2314332 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8837. Min Range: -6.8837
Max Act: 6.1650. Min Act: -0.1700
Data Index: 3591829 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19