Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3152 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2136. Min Range: -4.2136
Max Act: 4.2136. Min Act: -0.1700
Data Index: 8217091 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9635. Min Act: -0.1700
Data Index: 4909586 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9635. Min Act: -0.1700
Data Index: 6774220 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9323. Min Act: -0.1700
Data Index: 4670987 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9635. Min Act: -0.1700
Data Index: 6145977 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9010. Min Act: -0.1700
Data Index: 4171733 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8698. Min Act: -0.1700
Data Index: 6441691 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9010. Min Act: -0.1700
Data Index: 3482796 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9010. Min Act: -0.1700
Data Index: 6895632 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8698. Min Act: -0.1700
Data Index: 5003684 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9010. Min Act: -0.1700
Data Index: 839597 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8698. Min Act: -0.1700
Data Index: 7971001 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8698. Min Act: -0.1700
Data Index: 5841974 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.9010. Min Act: -0.1700
Data Index: 415517 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8385. Min Act: -0.1700
Data Index: 3951432 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8385. Min Act: -0.1700
Data Index: 3738109 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8385. Min Act: -0.1700
Data Index: 6071224 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8385. Min Act: -0.1700
Data Index: 6118084 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8385. Min Act: -0.1700
Data Index: 2338674 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2136. Min Range: -4.2136
Max Act: 3.8072. Min Act: -0.1700
Data Index: 6771595 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19