Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3892 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.4940. Min Act: -0.1699
Data Index: 1021198 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.4315. Min Act: -0.1700
Data Index: 2777913 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.3690. Min Act: -0.1700
Data Index: 500615 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.2752. Min Act: -0.1700
Data Index: 4987021 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.2440. Min Act: -0.1700
Data Index: 3526560 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.2127. Min Act: -0.1700
Data Index: 1439238 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.2127. Min Act: -0.1700
Data Index: 3301302 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.2127. Min Act: -0.1700
Data Index: 3199770 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1815. Min Act: -0.1700
Data Index: 1963146 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1502. Min Act: -0.1700
Data Index: 1778353 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1815. Min Act: -0.1700
Data Index: 5792584 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1502. Min Act: -0.1700
Data Index: 4545210 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1502. Min Act: -0.1700
Data Index: 2456721 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.0877. Min Act: -0.1700
Data Index: 7248495 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1190. Min Act: -0.1700
Data Index: 3630850 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1190. Min Act: -0.1700
Data Index: 4104108 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.1190. Min Act: -0.1700
Data Index: 164441 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.0877. Min Act: -0.1700
Data Index: 4732845 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.0565. Min Act: -0.1700
Data Index: 1439237 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4940. Min Range: -5.4940
Max Act: 5.0565. Min Act: -0.1700
Data Index: 95730 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19