Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5712 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.7064. Min Act: -0.1700
Data Index: 1554814 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.6439. Min Act: -0.1700
Data Index: 3196955 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.6127. Min Act: -0.1700
Data Index: 1456791 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.5814. Min Act: -0.1700
Data Index: 1250066 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.5502. Min Act: -0.1700
Data Index: 99640 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.5189. Min Act: -0.1700
Data Index: 3340996 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.5189. Min Act: -0.1700
Data Index: 2728844 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.5189. Min Act: -0.1700
Data Index: 7911244 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.4877. Min Act: -0.1700
Data Index: 1752922 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.4564. Min Act: -0.1700
Data Index: 2475280 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.4877. Min Act: -0.1700
Data Index: 2475281 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.4252. Min Act: -0.1700
Data Index: 6015038 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.4564. Min Act: -0.1700
Data Index: 6592477 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.4252. Min Act: -0.1700
Data Index: 8034754 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.3939. Min Act: -0.1700
Data Index: 2475283 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.3939. Min Act: -0.1700
Data Index: 6698580 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.3314. Min Act: -0.1700
Data Index: 8418336 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.3627. Min Act: -0.1700
Data Index: 6907825 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.3939. Min Act: -0.1700
Data Index: 6611933 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7064. Min Range: -5.7064
Max Act: 5.3627. Min Act: -0.1700
Data Index: 7749723 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19