Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.3784. Min Act: -0.1700
Data Index: 3209652 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.1596. Min Act: -0.1700
Data Index: 6609558 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.1596. Min Act: -0.1700
Data Index: 3548549 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.1284. Min Act: -0.1700
Data Index: 4320559 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.1284. Min Act: -0.1700
Data Index: 3363510 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.1284. Min Act: -0.1700
Data Index: 3666562 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0971. Min Act: -0.1700
Data Index: 3371639 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0659. Min Act: -0.1700
Data Index: 5988860 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0659. Min Act: -0.1700
Data Index: 2361319 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 3646896 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 6079461 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0034. Min Act: -0.1700
Data Index: 2665154 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 6643417 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0034. Min Act: -0.1700
Data Index: 6385369 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0034. Min Act: -0.1700
Data Index: 2509934 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0034. Min Act: -0.1700
Data Index: 2273806 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0346. Min Act: -0.1700
Data Index: 874234 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3784. Min Range: -5.3784
Max Act: 4.9721. Min Act: -0.1700
Data Index: 3584366 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0034. Min Act: -0.1700
Data Index: 1188074 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3784. Min Range: -5.3784
Max Act: 5.0034. Min Act: -0.1700
Data Index: 6481740 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19