Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.5610. Min Act: -0.1700
Data Index: 5416162 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.4673. Min Act: -0.1700
Data Index: 5879449 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.4360. Min Act: -0.1700
Data Index: 1113648 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.4048. Min Act: -0.1700
Data Index: 1610373 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.4048. Min Act: -0.1700
Data Index: 996773 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.3735. Min Act: -0.1700
Data Index: 5579750 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.3422. Min Act: -0.1700
Data Index: 566964 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.2797. Min Act: -0.1700
Data Index: 5256731 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.2485. Min Act: -0.1700
Data Index: 3224474 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.2797. Min Act: -0.1700
Data Index: 3051743 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.2797. Min Act: -0.1700
Data Index: 8120852 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.2485. Min Act: -0.1700
Data Index: 454258 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.3110. Min Act: -0.1700
Data Index: 6683615 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.2172. Min Act: -0.1700
Data Index: 5546727 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.2485. Min Act: -0.1700
Data Index: 4388036 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.2172. Min Act: -0.1700
Data Index: 1096330 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.1860. Min Act: -0.1700
Data Index: 7239633 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.1547. Min Act: -0.1700
Data Index: 5660337 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.1235. Min Act: -0.1700
Data Index: 3563864 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5610. Min Range: -4.5610
Max Act: 4.1547. Min Act: -0.1700
Data Index: 5080479 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19