Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 607 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1136. Min Range: -6.1136
Max Act: 6.0511. Min Act: -0.1700
Data Index: 1789977 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1136. Min Range: -6.1136
Max Act: 6.1136. Min Act: -0.1700
Data Index: 4087301 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1136. Min Range: -6.1136
Max Act: 6.0823. Min Act: -0.1700
Data Index: 544143 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1136. Min Range: -6.1136
Max Act: 6.0511. Min Act: -0.1700
Data Index: 8192304 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.9886. Min Act: -0.1700
Data Index: 2523372 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.9573. Min Act: -0.1700
Data Index: 1622017 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.9573. Min Act: -0.1700
Data Index: 3325448 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.9573. Min Act: -0.1700
Data Index: 3731236 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.9573. Min Act: -0.1700
Data Index: 3969167 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.9261. Min Act: -0.1700
Data Index: 3373244 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.8636. Min Act: -0.1700
Data Index: 3623082 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.8011. Min Act: -0.1700
Data Index: 4277394 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.7698. Min Act: -0.1700
Data Index: 425505 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.8011. Min Act: -0.1700
Data Index: 3668493 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.8011. Min Act: -0.1700
Data Index: 1956874 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.7386. Min Act: -0.1700
Data Index: 2399519 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.7386. Min Act: -0.1700
Data Index: 1746235 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.7073. Min Act: -0.1700
Data Index: 5731232 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.7386. Min Act: -0.1700
Data Index: 8523338 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1136. Min Range: -6.1136
Max Act: 5.7386. Min Act: -0.1700
Data Index: 3524403 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19