Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 998 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.6649. Min Act: -0.1700
Data Index: 1610124 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.5712. Min Act: -0.1700
Data Index: 7921688 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.4774. Min Act: -0.1700
Data Index: 3273363 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.4774. Min Act: -0.1700
Data Index: 8201170 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.4462. Min Act: -0.1700
Data Index: 1610108 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.4462. Min Act: -0.1700
Data Index: 5766854 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.4462. Min Act: -0.1700
Data Index: 6848766 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.4149. Min Act: -0.1700
Data Index: 5085944 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.4149. Min Act: -0.1700
Data Index: 7207011 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3837. Min Act: -0.1700
Data Index: 2847743 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3837. Min Act: -0.1700
Data Index: 4355662 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3837. Min Act: -0.1700
Data Index: 2847744 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3837. Min Act: -0.1700
Data Index: 6848770 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3524. Min Act: -0.1700
Data Index: 6531172 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3524. Min Act: -0.1700
Data Index: 4355651 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3212. Min Act: -0.1700
Data Index: 2650278 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3524. Min Act: -0.1700
Data Index: 2650279 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3212. Min Act: -0.1700
Data Index: 4355650 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3212. Min Act: -0.1700
Data Index: 6848775 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6649. Min Range: -5.6649
Max Act: 5.3524. Min Act: -0.1700
Data Index: 3298779 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19