Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6049. Min Range: -7.6049
Max Act: 7.6049. Min Act: -0.1700
Data Index: 2717670 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6049. Min Range: -7.6049
Max Act: 7.0736. Min Act: -0.1700
Data Index: 7513463 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6049. Min Range: -7.6049
Max Act: 7.0424. Min Act: -0.1700
Data Index: 7989289 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6049. Min Range: -7.6049
Max Act: 7.0111. Min Act: -0.1700
Data Index: 1782812 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.9799. Min Act: -0.1700
Data Index: 1210852 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.9486. Min Act: -0.1700
Data Index: 2460003 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.9486. Min Act: -0.1700
Data Index: 3229512 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.9799. Min Act: -0.1700
Data Index: 5262734 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.8861. Min Act: -0.1700
Data Index: 1303611 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.8861. Min Act: -0.1700
Data Index: 5542491 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.8549. Min Act: -0.1700
Data Index: 8248329 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.8549. Min Act: -0.1700
Data Index: 221885 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.8236. Min Act: -0.1700
Data Index: 8623143 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.7924. Min Act: -0.1700
Data Index: 2215545 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.7611. Min Act: -0.1700
Data Index: 4773610 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.7924. Min Act: -0.1700
Data Index: 5512737 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.7299. Min Act: -0.1700
Data Index: 5991824 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.7299. Min Act: -0.1700
Data Index: 4788851 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.6986. Min Act: -0.1700
Data Index: 8748277 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6049. Min Range: -7.6049
Max Act: 6.7299. Min Act: -0.1700
Data Index: 2983200 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19