Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5301 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.6373. Min Act: -0.1700
Data Index: 2233204 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.3873. Min Act: -0.1700
Data Index: 5469640 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.3873. Min Act: -0.1700
Data Index: 4317394 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.3248. Min Act: -0.1700
Data Index: 7258770 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.3248. Min Act: -0.1700
Data Index: 6233472 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.3248. Min Act: -0.1700
Data Index: 1739870 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.2623. Min Act: -0.1700
Data Index: 5217159 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.2623. Min Act: -0.1700
Data Index: 7533432 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.2623. Min Act: -0.1700
Data Index: 4168690 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.2623. Min Act: -0.1700
Data Index: 5808804 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.1998. Min Act: -0.1700
Data Index: 6552051 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.1998. Min Act: -0.1700
Data Index: 1254049 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.1998. Min Act: -0.1700
Data Index: 1589682 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.1998. Min Act: -0.1700
Data Index: 937830 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.1373. Min Act: -0.1700
Data Index: 911578 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.0748. Min Act: -0.1700
Data Index: 4390773 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.1373. Min Act: -0.1700
Data Index: 1674682 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.1373. Min Act: -0.1700
Data Index: 2399362 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.1373. Min Act: -0.1700
Data Index: 2330885 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6373. Min Range: -8.6373
Max Act: 8.1373. Min Act: -0.1700
Data Index: 5541561 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19