Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4191 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1624. Min Range: -5.1624
Max Act: 5.1624. Min Act: -0.1700
Data Index: 2294552 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1624. Min Range: -5.1624
Max Act: 5.0062. Min Act: -0.1700
Data Index: 852958 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.9437. Min Act: -0.1700
Data Index: 7877202 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.9749. Min Act: -0.1700
Data Index: 3803987 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.9124. Min Act: -0.1700
Data Index: 26337 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.7562. Min Act: -0.1700
Data Index: 558506 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.7249. Min Act: -0.1700
Data Index: 5071660 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.7249. Min Act: -0.1700
Data Index: 307228 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.6937. Min Act: -0.1700
Data Index: 3961299 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.6624. Min Act: -0.1700
Data Index: 8704388 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.6312. Min Act: -0.1700
Data Index: 4697188 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.6312. Min Act: -0.1700
Data Index: 6976161 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.5687. Min Act: -0.1700
Data Index: 839905 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.5687. Min Act: -0.1700
Data Index: 4111238 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.5374. Min Act: -0.1700
Data Index: 2736512 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.5374. Min Act: -0.1700
Data Index: 3990441 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.5374. Min Act: -0.1700
Data Index: 2662721 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.5374. Min Act: -0.1700
Data Index: 7576770 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.4749. Min Act: -0.1700
Data Index: 7588856 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1624. Min Range: -5.1624
Max Act: 4.5062. Min Act: -0.1700
Data Index: 7651874 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19