Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3099 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0085. Min Range: -5.0085
Max Act: 5.0085. Min Act: -0.1700
Data Index: 2947314 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.9148. Min Act: -0.1700
Data Index: 6577923 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.7898. Min Act: -0.1700
Data Index: 8014020 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.7273. Min Act: -0.1700
Data Index: 3131128 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.6023. Min Act: -0.1700
Data Index: 6024033 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.5710. Min Act: -0.1700
Data Index: 97095 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.5398. Min Act: -0.1700
Data Index: 833254 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.5398. Min Act: -0.1700
Data Index: 7926918 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.5398. Min Act: -0.1700
Data Index: 5812705 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4773. Min Act: -0.1700
Data Index: 1403549 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.5085. Min Act: -0.1700
Data Index: 6166318 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4773. Min Act: -0.1700
Data Index: 160209 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4773. Min Act: -0.1700
Data Index: 7651033 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4773. Min Act: -0.1700
Data Index: 4198859 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4773. Min Act: -0.1700
Data Index: 2692166 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4773. Min Act: -0.1700
Data Index: 529650 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4460. Min Act: -0.1700
Data Index: 5367110 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4148. Min Act: -0.1700
Data Index: 6067090 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4460. Min Act: -0.1700
Data Index: 4240520 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0085. Min Range: -5.0085
Max Act: 4.4773. Min Act: -0.1700
Data Index: 3053537 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19