Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3971 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.7551. Min Act: -0.1700
Data Index: 4371783 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.7551. Min Act: -0.1700
Data Index: 3751172 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.7239. Min Act: -0.1700
Data Index: 1336076 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.7551. Min Act: -0.1700
Data Index: 3082514 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.5989. Min Act: -0.1700
Data Index: 7002296 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.6301. Min Act: -0.1700
Data Index: 6478502 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.5364. Min Act: -0.1700
Data Index: 7239156 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.5051. Min Act: -0.1700
Data Index: 3199149 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.5051. Min Act: -0.1700
Data Index: 3355830 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.4426. Min Act: -0.1700
Data Index: 5051589 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.4426. Min Act: -0.1700
Data Index: 4386815 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.3801. Min Act: -0.1700
Data Index: 7960510 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.3801. Min Act: -0.1700
Data Index: 3531638 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.3489. Min Act: -0.1700
Data Index: 6445204 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.3176. Min Act: -0.1700
Data Index: 50782 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.3489. Min Act: -0.1700
Data Index: 2570749 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.3489. Min Act: -0.1700
Data Index: 1438612 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.3176. Min Act: -0.1700
Data Index: 1183496 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.2864. Min Act: -0.1700
Data Index: 776622 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7551. Min Range: -5.7551
Max Act: 5.3176. Min Act: -0.1700
Data Index: 6880047 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19