Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3396 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.7605. Min Act: -0.1700
Data Index: 6495042 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.6980. Min Act: -0.1700
Data Index: 3485838 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.4168. Min Act: -0.1700
Data Index: 8003512 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.2293. Min Act: -0.1700
Data Index: 7411250 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.2293. Min Act: -0.1700
Data Index: 886218 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.1668. Min Act: -0.1700
Data Index: 5594323 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.1043. Min Act: -0.1700
Data Index: 1537712 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.0730. Min Act: -0.1700
Data Index: 5590733 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.0418. Min Act: -0.1700
Data Index: 1992966 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.0418. Min Act: -0.1700
Data Index: 5033036 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.0105. Min Act: -0.1700
Data Index: 5423081 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7605. Min Range: -5.7605
Max Act: 5.0105. Min Act: -0.1700
Data Index: 6112206 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7605. Min Range: -5.7605
Max Act: 4.9793. Min Act: -0.1700
Data Index: 5529870 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7605. Min Range: -5.7605
Max Act: 4.9793. Min Act: -0.1700
Data Index: 4007078 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7605. Min Range: -5.7605
Max Act: 4.9480. Min Act: -0.1700
Data Index: 5383059 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7605. Min Range: -5.7605
Max Act: 4.9168. Min Act: -0.1700
Data Index: 5448054 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7605. Min Range: -5.7605
Max Act: 4.9168. Min Act: -0.1700
Data Index: 3190472 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7605. Min Range: -5.7605
Max Act: 4.9168. Min Act: -0.1700
Data Index: 5851352 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7605. Min Range: -5.7605
Max Act: 4.9480. Min Act: -0.1700
Data Index: 7192758 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7605. Min Range: -5.7605
Max Act: 4.9168. Min Act: -0.1700
Data Index: 314175 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19