Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4787 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3203. Min Range: -6.3203
Max Act: 6.3203. Min Act: -0.1700
Data Index: 6043345 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3203. Min Range: -6.3203
Max Act: 6.2578. Min Act: -0.1700
Data Index: 8210686 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3203. Min Range: -6.3203
Max Act: 6.1015. Min Act: -0.1700
Data Index: 7837989 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3203. Min Range: -6.3203
Max Act: 6.0390. Min Act: -0.1700
Data Index: 6515538 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.9140. Min Act: -0.1700
Data Index: 6151919 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.9140. Min Act: -0.1700
Data Index: 3236681 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.8515. Min Act: -0.1700
Data Index: 6168610 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.8203. Min Act: -0.1700
Data Index: 5150407 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.8203. Min Act: -0.1700
Data Index: 2804996 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.7890. Min Act: -0.1700
Data Index: 8095695 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.7890. Min Act: -0.1700
Data Index: 2796837 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.7890. Min Act: -0.1700
Data Index: 6956116 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.7578. Min Act: -0.1700
Data Index: 4886002 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.7265. Min Act: -0.1700
Data Index: 2897007 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.6953. Min Act: -0.1700
Data Index: 4728262 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.6953. Min Act: -0.1700
Data Index: 6903330 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.6953. Min Act: -0.1700
Data Index: 1922376 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.6953. Min Act: -0.1700
Data Index: 4778096 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.6953. Min Act: -0.1700
Data Index: 1060962 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3203. Min Range: -6.3203
Max Act: 5.6953. Min Act: -0.1700
Data Index: 6312745 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19