Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5865 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0342. Min Range: -7.0342
Max Act: 7.0342. Min Act: -0.1700
Data Index: 584868 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.8155. Min Act: -0.1700
Data Index: 5269766 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.7217. Min Act: -0.1700
Data Index: 5834700 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.7217. Min Act: -0.1700
Data Index: 87642 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.7217. Min Act: -0.1700
Data Index: 1205946 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.6280. Min Act: -0.1700
Data Index: 566027 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.5030. Min Act: -0.1700
Data Index: 2862965 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.4717. Min Act: -0.1700
Data Index: 780923 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.4717. Min Act: -0.1700
Data Index: 5178389 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.4717. Min Act: -0.1700
Data Index: 6150644 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.3467. Min Act: -0.1700
Data Index: 553850 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.3467. Min Act: -0.1700
Data Index: 3678759 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.3155. Min Act: -0.1700
Data Index: 7030424 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.3155. Min Act: -0.1700
Data Index: 5493655 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.3155. Min Act: -0.1700
Data Index: 7854991 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.2530. Min Act: -0.1700
Data Index: 2876708 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.2842. Min Act: -0.1700
Data Index: 6587159 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.2842. Min Act: -0.1700
Data Index: 4055823 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.3155. Min Act: -0.1700
Data Index: 2559066 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0342. Min Range: -7.0342
Max Act: 6.2842. Min Act: -0.1700
Data Index: 3486194 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19