Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4119 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2491. Min Range: -5.2491
Max Act: 5.2491. Min Act: -0.1700
Data Index: 1701917 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2491. Min Range: -5.2491
Max Act: 5.1553. Min Act: -0.1700
Data Index: 7365789 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.9053. Min Act: -0.1700
Data Index: 7756182 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.9053. Min Act: -0.1700
Data Index: 6361054 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.8741. Min Act: -0.1700
Data Index: 8254460 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.8741. Min Act: -0.1700
Data Index: 4800568 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.8428. Min Act: -0.1700
Data Index: 31765 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.8116. Min Act: -0.1700
Data Index: 3658229 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.8116. Min Act: -0.1700
Data Index: 1586159 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.8116. Min Act: -0.1700
Data Index: 6695971 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.8428. Min Act: -0.1700
Data Index: 6902382 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.8116. Min Act: -0.1700
Data Index: 2670715 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.7803. Min Act: -0.1700
Data Index: 8209985 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.7803. Min Act: -0.1700
Data Index: 7434394 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.7803. Min Act: -0.1700
Data Index: 559821 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.7803. Min Act: -0.1700
Data Index: 3622681 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.7803. Min Act: -0.1700
Data Index: 7503333 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.7803. Min Act: -0.1700
Data Index: 2628990 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.7803. Min Act: -0.1700
Data Index: 1590031 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2491. Min Range: -5.2491
Max Act: 4.7803. Min Act: -0.1700
Data Index: 7702322 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19