Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4642 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6247. Min Range: -7.6247
Max Act: 7.6247. Min Act: -0.1700
Data Index: 3775747 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6247. Min Range: -7.6247
Max Act: 7.4372. Min Act: -0.1700
Data Index: 5015587 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6247. Min Range: -7.6247
Max Act: 7.1872. Min Act: -0.1700
Data Index: 5472501 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6247. Min Range: -7.6247
Max Act: 7.1247. Min Act: -0.1700
Data Index: 6512977 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6247. Min Range: -7.6247
Max Act: 7.0310. Min Act: -0.1700
Data Index: 7972044 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.9997. Min Act: -0.1700
Data Index: 5514020 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.8435. Min Act: -0.1700
Data Index: 7935653 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.7497. Min Act: -0.1700
Data Index: 8132439 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.7185. Min Act: -0.1700
Data Index: 6980911 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.6872. Min Act: -0.1700
Data Index: 3042605 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.6247. Min Act: -0.1700
Data Index: 1514118 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.6872. Min Act: -0.1700
Data Index: 2419935 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.6247. Min Act: -0.1700
Data Index: 4075024 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.5935. Min Act: -0.1700
Data Index: 1327615 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.5935. Min Act: -0.1700
Data Index: 5482616 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.5935. Min Act: -0.1700
Data Index: 3631624 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.5622. Min Act: -0.1700
Data Index: 135166 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.5622. Min Act: -0.1700
Data Index: 1272536 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.5622. Min Act: -0.1700
Data Index: 4466465 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6247. Min Range: -7.6247
Max Act: 6.5622. Min Act: -0.1700
Data Index: 4861508 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19