Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5386 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.8291. Min Act: -0.1700
Data Index: 5048130 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.7666. Min Act: -0.1700
Data Index: 5094126 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6728. Min Act: -0.1700
Data Index: 533803 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.7041. Min Act: -0.1700
Data Index: 2283405 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6728. Min Act: -0.1700
Data Index: 7496030 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6728. Min Act: -0.1700
Data Index: 4441658 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 5185294 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 8427390 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6416. Min Act: -0.1700
Data Index: 2412034 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 6585952 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 650713 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 5119735 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 2200358 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 6927566 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.5791. Min Act: -0.1700
Data Index: 3850202 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.5791. Min Act: -0.1700
Data Index: 7735928 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.6103. Min Act: -0.1700
Data Index: 127888 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.5791. Min Act: -0.1700
Data Index: 6389500 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.5791. Min Act: -0.1700
Data Index: 112379 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8291. Min Range: -5.8291
Max Act: 5.5791. Min Act: -0.1700
Data Index: 6757993 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19