Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6232 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0600. Min Range: -5.0600
Max Act: 5.0600. Min Act: -0.1700
Data Index: 8037278 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.9975. Min Act: -0.1700
Data Index: 5485707 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.9975. Min Act: -0.1700
Data Index: 1711287 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.9662. Min Act: -0.1700
Data Index: 8278814 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.9350. Min Act: -0.1700
Data Index: 8125849 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.9037. Min Act: -0.1700
Data Index: 5861645 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.9350. Min Act: -0.1700
Data Index: 8212269 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.9037. Min Act: -0.1700
Data Index: 6494130 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.8725. Min Act: -0.1700
Data Index: 8363042 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.8725. Min Act: -0.1700
Data Index: 1827947 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.8412. Min Act: -0.1700
Data Index: 3409378 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.8100. Min Act: -0.1700
Data Index: 2294336 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.8100. Min Act: -0.1700
Data Index: 4043148 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.8100. Min Act: -0.1700
Data Index: 7043079 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.7787. Min Act: -0.1700
Data Index: 7118228 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.7787. Min Act: -0.1700
Data Index: 7532083 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.7475. Min Act: -0.1700
Data Index: 1657656 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.7162. Min Act: -0.1700
Data Index: 7365488 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.7162. Min Act: -0.1700
Data Index: 2242595 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0600. Min Range: -5.0600
Max Act: 4.6850. Min Act: -0.1700
Data Index: 2877705 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19