Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5892 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.8842. Min Act: -0.1700
Data Index: 8688556 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.8842. Min Act: -0.1700
Data Index: 3216576 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.8530. Min Act: -0.1700
Data Index: 4461956 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.8530. Min Act: -0.1700
Data Index: 902196 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.8217. Min Act: -0.1700
Data Index: 249702 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.7905. Min Act: -0.1700
Data Index: 8027837 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.7905. Min Act: -0.1700
Data Index: 3438101 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.7905. Min Act: -0.1700
Data Index: 1421233 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.7592. Min Act: -0.1700
Data Index: 2721911 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.7592. Min Act: -0.1700
Data Index: 8706987 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.7280. Min Act: -0.1700
Data Index: 971505 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.6967. Min Act: -0.1700
Data Index: 431645 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.7280. Min Act: -0.1700
Data Index: 7345203 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.7280. Min Act: -0.1700
Data Index: 7423395 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.6655. Min Act: -0.1700
Data Index: 8611514 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.6655. Min Act: -0.1700
Data Index: 3482577 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.6655. Min Act: -0.1700
Data Index: 7390941 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.6030. Min Act: -0.1700
Data Index: 7163529 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.6342. Min Act: -0.1700
Data Index: 1117803 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8842. Min Range: -4.8842
Max Act: 4.6030. Min Act: -0.1700
Data Index: 5380270 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19