Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2571 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.4288. Min Act: -0.1700
Data Index: 1105184 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.4601. Min Act: -0.1700
Data Index: 8007575 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.3976. Min Act: -0.1700
Data Index: 6479495 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.3976. Min Act: -0.1700
Data Index: 3326970 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.2101. Min Act: -0.1700
Data Index: 7512405 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.1476. Min Act: -0.1700
Data Index: 279989 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.1163. Min Act: -0.1700
Data Index: 3021915 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.0851. Min Act: -0.1700
Data Index: 1648710 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.0538. Min Act: -0.1700
Data Index: 1354796 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.0538. Min Act: -0.1700
Data Index: 1105950 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.0538. Min Act: -0.1700
Data Index: 48116 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.0226. Min Act: -0.1700
Data Index: 7212331 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4601. Min Range: -5.4601
Max Act: 5.0226. Min Act: -0.1700
Data Index: 4251097 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4601. Min Range: -5.4601
Max Act: 4.9913. Min Act: -0.1700
Data Index: 3794085 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4601. Min Range: -5.4601
Max Act: 4.9913. Min Act: -0.1700
Data Index: 3220953 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4601. Min Range: -5.4601
Max Act: 4.9601. Min Act: -0.1700
Data Index: 4334177 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4601. Min Range: -5.4601
Max Act: 4.9913. Min Act: -0.1700
Data Index: 3752780 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4601. Min Range: -5.4601
Max Act: 4.9601. Min Act: -0.1700
Data Index: 1441942 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4601. Min Range: -5.4601
Max Act: 4.9601. Min Act: -0.1700
Data Index: 5842165 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4601. Min Range: -5.4601
Max Act: 4.9601. Min Act: -0.1700
Data Index: 5526162 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19