Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.6031. Min Act: -0.1700
Data Index: 3057968 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.6031. Min Act: -0.1700
Data Index: 3879644 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.4087. Min Act: -0.1700
Data Index: 8493899 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.3924. Min Act: -0.1700
Data Index: 175247 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.3760. Min Act: -0.1700
Data Index: 3133221 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.3433. Min Act: -0.1700
Data Index: 3884770 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.3269. Min Act: -0.1700
Data Index: 1384633 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.3105. Min Act: -0.1700
Data Index: 5600871 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.3105. Min Act: -0.1700
Data Index: 8476594 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.3105. Min Act: -0.1700
Data Index: 2062283 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.3105. Min Act: -0.1700
Data Index: 8620014 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.2940. Min Act: -0.1700
Data Index: 6966766 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.2775. Min Act: -0.1700
Data Index: 6658098 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.2775. Min Act: -0.1700
Data Index: 7599319 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.2611. Min Act: -0.1700
Data Index: 2313530 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.2280. Min Act: -0.1700
Data Index: 3293540 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.2445. Min Act: -0.1700
Data Index: 6218878 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.2445. Min Act: -0.1700
Data Index: 7940303 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.2280. Min Act: -0.1700
Data Index: 8817567 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6031. Min Range: -2.6031
Max Act: 2.2114. Min Act: -0.1700
Data Index: 3293539 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19