Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3568 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0772. Min Range: -5.0772
Max Act: 5.0772. Min Act: -0.1700
Data Index: 602986 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.9835. Min Act: -0.1700
Data Index: 2554738 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.9835. Min Act: -0.1700
Data Index: 8206540 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.9210. Min Act: -0.1700
Data Index: 6208218 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.9522. Min Act: -0.1700
Data Index: 1224516 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.8897. Min Act: -0.1700
Data Index: 806644 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.8585. Min Act: -0.1700
Data Index: 2604135 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.8585. Min Act: -0.1700
Data Index: 3717653 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.8585. Min Act: -0.1700
Data Index: 5606647 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.8272. Min Act: -0.1700
Data Index: 8406091 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.8272. Min Act: -0.1700
Data Index: 7799003 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.8272. Min Act: -0.1700
Data Index: 1482698 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.7960. Min Act: -0.1700
Data Index: 191808 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.7960. Min Act: -0.1700
Data Index: 3861918 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.8272. Min Act: -0.1700
Data Index: 5330728 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.8272. Min Act: -0.1700
Data Index: 598955 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.7960. Min Act: -0.1700
Data Index: 4212998 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.7960. Min Act: -0.1700
Data Index: 4544935 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.7960. Min Act: -0.1700
Data Index: 2862117 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0772. Min Range: -5.0772
Max Act: 4.7960. Min Act: -0.1700
Data Index: 2739691 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19