Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3729. Min Range: -7.3729
Max Act: 7.3729. Min Act: -0.1700
Data Index: 7934270 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3729. Min Range: -7.3729
Max Act: 7.2479. Min Act: -0.1700
Data Index: 4381178 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3729. Min Range: -7.3729
Max Act: 7.1229. Min Act: -0.1700
Data Index: 641002 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.9979. Min Act: -0.1700
Data Index: 8123357 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.9666. Min Act: -0.1700
Data Index: 6685057 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.9666. Min Act: -0.1700
Data Index: 7209989 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.9666. Min Act: -0.1700
Data Index: 4278871 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.9354. Min Act: -0.1700
Data Index: 4612770 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.9354. Min Act: -0.1700
Data Index: 5043255 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.9041. Min Act: -0.1700
Data Index: 1339750 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.8729. Min Act: -0.1700
Data Index: 4911685 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.8416. Min Act: -0.1700
Data Index: 3629864 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.8416. Min Act: -0.1700
Data Index: 3606732 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.8416. Min Act: -0.1700
Data Index: 1296977 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.8104. Min Act: -0.1700
Data Index: 227393 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.7479. Min Act: -0.1700
Data Index: 852783 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.7166. Min Act: -0.1700
Data Index: 3126399 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.7479. Min Act: -0.1700
Data Index: 6670827 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.7479. Min Act: -0.1700
Data Index: 5981108 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3729. Min Range: -7.3729
Max Act: 6.7166. Min Act: -0.1700
Data Index: 5425026 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19