Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.9629. Min Act: -0.1700
Data Index: 8828876 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.9317. Min Act: -0.1700
Data Index: 737925 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.9004. Min Act: -0.1700
Data Index: 6074343 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.9004. Min Act: -0.1700
Data Index: 5903917 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.8692. Min Act: -0.1700
Data Index: 1434195 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.8379. Min Act: -0.1700
Data Index: 41535 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.8379. Min Act: -0.1700
Data Index: 6417823 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.8692. Min Act: -0.1700
Data Index: 777940 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.8692. Min Act: -0.1700
Data Index: 4470805 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.8067. Min Act: -0.1700
Data Index: 6348383 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.8379. Min Act: -0.1700
Data Index: 3717616 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.8067. Min Act: -0.1700
Data Index: 7040548 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.7754. Min Act: -0.1700
Data Index: 477985 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.7442. Min Act: -0.1700
Data Index: 6465896 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.7442. Min Act: -0.1700
Data Index: 478121 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.7442. Min Act: -0.1700
Data Index: 8522705 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.7442. Min Act: -0.1700
Data Index: 2470413 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.7129. Min Act: -0.1700
Data Index: 5069015 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.7129. Min Act: -0.1700
Data Index: 3449027 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9629. Min Range: -5.9629
Max Act: 5.7129. Min Act: -0.1700
Data Index: 7308685 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19