Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5790 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3469. Min Range: -7.3469
Max Act: 7.3469. Min Act: -0.1700
Data Index: 1600564 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3469. Min Range: -7.3469
Max Act: 7.1906. Min Act: -0.1700
Data Index: 2194288 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3469. Min Range: -7.3469
Max Act: 7.2531. Min Act: -0.1700
Data Index: 2299968 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3469. Min Range: -7.3469
Max Act: 7.0656. Min Act: -0.1700
Data Index: 8191376 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3469. Min Range: -7.3469
Max Act: 7.0656. Min Act: -0.1700
Data Index: 1261998 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3469. Min Range: -7.3469
Max Act: 7.0344. Min Act: -0.1700
Data Index: 7717642 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3469. Min Range: -7.3469
Max Act: 7.0344. Min Act: -0.1700
Data Index: 6506589 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.9406. Min Act: -0.1700
Data Index: 7814223 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.8781. Min Act: -0.1700
Data Index: 5018350 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.8156. Min Act: -0.1700
Data Index: 1343199 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.8469. Min Act: -0.1700
Data Index: 1466692 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.8469. Min Act: -0.1700
Data Index: 1757083 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.8469. Min Act: -0.1700
Data Index: 7784889 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.8156. Min Act: -0.1700
Data Index: 3528938 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.8156. Min Act: -0.1700
Data Index: 6787473 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.8156. Min Act: -0.1700
Data Index: 6506590 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.8156. Min Act: -0.1700
Data Index: 4641802 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.7844. Min Act: -0.1700
Data Index: 864104 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.7844. Min Act: -0.1700
Data Index: 6455674 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3469. Min Range: -7.3469
Max Act: 6.7844. Min Act: -0.1700
Data Index: 4931444 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19