Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.9467. Min Act: -0.1700
Data Index: 1044361 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.4467. Min Act: -0.1700
Data Index: 490806 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.4467. Min Act: -0.1700
Data Index: 8352553 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.3842. Min Act: -0.1700
Data Index: 7419815 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.2280. Min Act: -0.1700
Data Index: 3526266 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.1655. Min Act: -0.1700
Data Index: 2259878 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.1655. Min Act: -0.1700
Data Index: 4661723 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.1342. Min Act: -0.1700
Data Index: 8098325 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.1342. Min Act: -0.1700
Data Index: 1220159 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.1342. Min Act: -0.1700
Data Index: 2569138 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.1030. Min Act: -0.1700
Data Index: 7437703 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.0405. Min Act: -0.1700
Data Index: 5113129 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.0405. Min Act: -0.1700
Data Index: 2347450 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9467. Min Range: -7.9467
Max Act: 7.0405. Min Act: -0.1700
Data Index: 6114464 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9467. Min Range: -7.9467
Max Act: 6.9780. Min Act: -0.1700
Data Index: 367060 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9467. Min Range: -7.9467
Max Act: 6.9467. Min Act: -0.1700
Data Index: 8794453 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9467. Min Range: -7.9467
Max Act: 6.9780. Min Act: -0.1700
Data Index: 2572725 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9467. Min Range: -7.9467
Max Act: 6.9467. Min Act: -0.1700
Data Index: 2092265 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9467. Min Range: -7.9467
Max Act: 6.9467. Min Act: -0.1700
Data Index: 3886265 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9467. Min Range: -7.9467
Max Act: 6.9780. Min Act: -0.1700
Data Index: 2906293 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19