Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1774 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.7810. Min Act: -0.1700
Data Index: 274212 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.7185. Min Act: -0.1700
Data Index: 5986569 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.6872. Min Act: -0.1700
Data Index: 1890362 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.6872. Min Act: -0.1700
Data Index: 5343911 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.6247. Min Act: -0.1700
Data Index: 776520 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.5935. Min Act: -0.1700
Data Index: 8708945 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.5622. Min Act: -0.1700
Data Index: 209115 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.5310. Min Act: -0.1700
Data Index: 3941849 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.4997. Min Act: -0.1700
Data Index: 6301538 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.3747. Min Act: -0.1700
Data Index: 4598258 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.3747. Min Act: -0.1700
Data Index: 4776847 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.3435. Min Act: -0.1700
Data Index: 4362918 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.3122. Min Act: -0.1700
Data Index: 835567 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2810. Min Act: -0.1700
Data Index: 7147064 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2810. Min Act: -0.1700
Data Index: 571043 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2810. Min Act: -0.1700
Data Index: 5751090 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2810. Min Act: -0.1700
Data Index: 6782626 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2497. Min Act: -0.1700
Data Index: 3081317 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2497. Min Act: -0.1700
Data Index: 8300368 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7810. Min Range: -6.7810
Max Act: 6.2497. Min Act: -0.1700
Data Index: 6744174 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19