Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6224 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.9179. Min Act: -0.1700
Data Index: 1844299 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.7929. Min Act: -0.1700
Data Index: 4751278 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.7929. Min Act: -0.1700
Data Index: 2200040 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.7304. Min Act: -0.1700
Data Index: 7746924 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.6679. Min Act: -0.1700
Data Index: 4871578 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.5429. Min Act: -0.1700
Data Index: 8680336 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.4804. Min Act: -0.1700
Data Index: 6969777 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.3554. Min Act: -0.1700
Data Index: 8435739 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.4179. Min Act: -0.1700
Data Index: 8178259 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.4179. Min Act: -0.1700
Data Index: 8668710 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.3554. Min Act: -0.1700
Data Index: 8029681 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.3554. Min Act: -0.1700
Data Index: 8315794 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.2304. Min Act: -0.1700
Data Index: 878398 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.2929. Min Act: -0.1700
Data Index: 1576996 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.1679. Min Act: -0.1700
Data Index: 8265870 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.1679. Min Act: -0.1700
Data Index: 8315792 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.1679. Min Act: -0.1700
Data Index: 1201012 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.0429. Min Act: -0.1700
Data Index: 6143694 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.1054. Min Act: -0.1700
Data Index: 7106747 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9179. Min Range: -9.9179
Max Act: 9.1054. Min Act: -0.1700
Data Index: 878399 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19