Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.6145. Min Act: -0.1700
Data Index: 482908 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.3645. Min Act: -0.1700
Data Index: 2354455 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.2395. Min Act: -0.1700
Data Index: 727175 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.1770. Min Act: -0.1700
Data Index: 4141794 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.1145. Min Act: -0.1700
Data Index: 8260445 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.1145. Min Act: -0.1700
Data Index: 1727245 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.1145. Min Act: -0.1700
Data Index: 930342 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.1145. Min Act: -0.1700
Data Index: 6420243 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.0520. Min Act: -0.1700
Data Index: 3868529 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9895. Min Act: -0.1700
Data Index: 8436709 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6145. Min Range: -9.6145
Max Act: 9.0520. Min Act: -0.1700
Data Index: 2435384 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9895. Min Act: -0.1700
Data Index: 7290071 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9895. Min Act: -0.1700
Data Index: 5254599 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9270. Min Act: -0.1700
Data Index: 4334707 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9270. Min Act: -0.1700
Data Index: 4229313 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9895. Min Act: -0.1700
Data Index: 3200266 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9270. Min Act: -0.1700
Data Index: 1602792 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9270. Min Act: -0.1700
Data Index: 7294548 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9270. Min Act: -0.1700
Data Index: 7628714 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6145. Min Range: -9.6145
Max Act: 8.9270. Min Act: -0.1700
Data Index: 5285065 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19