Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4530. Min Range: -6.4530
Max Act: 6.4530. Min Act: -0.1700
Data Index: 7152845 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4530. Min Range: -6.4530
Max Act: 6.4217. Min Act: -0.1700
Data Index: 990711 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4530. Min Range: -6.4530
Max Act: 6.3905. Min Act: -0.1700
Data Index: 5054695 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4530. Min Range: -6.4530
Max Act: 6.2030. Min Act: -0.1700
Data Index: 6874322 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4530. Min Range: -6.4530
Max Act: 6.1405. Min Act: -0.1700
Data Index: 6514804 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4530. Min Range: -6.4530
Max Act: 6.1405. Min Act: -0.1700
Data Index: 801476 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4530. Min Range: -6.4530
Max Act: 6.0467. Min Act: -0.1700
Data Index: 1069233 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4530. Min Range: -6.4530
Max Act: 6.0467. Min Act: -0.1700
Data Index: 7599446 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4530. Min Range: -6.4530
Max Act: 6.0467. Min Act: -0.1700
Data Index: 1805539 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.9530. Min Act: -0.1700
Data Index: 1982044 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.9530. Min Act: -0.1700
Data Index: 3161544 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.9530. Min Act: -0.1700
Data Index: 8513122 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.9217. Min Act: -0.1700
Data Index: 5563675 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.9217. Min Act: -0.1700
Data Index: 7797488 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.9217. Min Act: -0.1700
Data Index: 256648 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.9217. Min Act: -0.1700
Data Index: 1428712 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.9217. Min Act: -0.1700
Data Index: 4211684 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.9217. Min Act: -0.1700
Data Index: 3515189 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.8905. Min Act: -0.1700
Data Index: 5326731 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4530. Min Range: -6.4530
Max Act: 5.8592. Min Act: -0.1700
Data Index: 3939023 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19