Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.6526. Min Act: -0.1700
Data Index: 4408936 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.5901. Min Act: -0.1700
Data Index: 129808 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.5276. Min Act: -0.1700
Data Index: 3794878 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.4964. Min Act: -0.1700
Data Index: 7530055 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.3714. Min Act: -0.1700
Data Index: 4984226 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.3714. Min Act: -0.1700
Data Index: 6207589 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.3714. Min Act: -0.1700
Data Index: 3527969 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.3089. Min Act: -0.1699
Data Index: 8633224 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.3401. Min Act: -0.1700
Data Index: 2496743 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.3089. Min Act: -0.1700
Data Index: 3474039 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.2776. Min Act: -0.1700
Data Index: 4206144 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.2776. Min Act: -0.1700
Data Index: 2753175 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.2464. Min Act: -0.1699
Data Index: 2892091 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.2464. Min Act: -0.1700
Data Index: 5451915 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.2151. Min Act: -0.1700
Data Index: 6965499 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.1839. Min Act: -0.1700
Data Index: 6732032 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.2151. Min Act: -0.1700
Data Index: 3266342 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.1839. Min Act: -0.1700
Data Index: 52126 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.1526. Min Act: -0.1700
Data Index: 4920885 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6526. Min Range: -6.6526
Max Act: 6.1214. Min Act: -0.1700
Data Index: 1868937 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19