Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5502 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8978. Min Range: -6.8978
Max Act: 6.8978. Min Act: -0.1700
Data Index: 3819148 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8978. Min Range: -6.8978
Max Act: 6.1791. Min Act: -0.1700
Data Index: 8658208 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8978. Min Range: -6.8978
Max Act: 6.0541. Min Act: -0.1700
Data Index: 6761661 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.9916. Min Act: -0.1700
Data Index: 7239426 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.9603. Min Act: -0.1700
Data Index: 8207189 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.9291. Min Act: -0.1700
Data Index: 3593913 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.8978. Min Act: -0.1700
Data Index: 165099 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.8978. Min Act: -0.1700
Data Index: 4167608 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.8041. Min Act: -0.1700
Data Index: 4575147 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.8041. Min Act: -0.1700
Data Index: 361374 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.7728. Min Act: -0.1700
Data Index: 5183927 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.8041. Min Act: -0.1700
Data Index: 431514 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.7416. Min Act: -0.1700
Data Index: 8097763 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.7103. Min Act: -0.1700
Data Index: 1209623 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.6791. Min Act: -0.1700
Data Index: 2810501 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.6478. Min Act: -0.1700
Data Index: 4619677 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.6478. Min Act: -0.1700
Data Index: 4885385 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.6478. Min Act: -0.1700
Data Index: 4830468 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.6478. Min Act: -0.1700
Data Index: 5011910 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8978. Min Range: -6.8978
Max Act: 5.6166. Min Act: -0.1700
Data Index: 1466362 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19