Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.7554. Min Act: -0.1700
Data Index: 170917 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.7554. Min Act: -0.1700
Data Index: 3615346 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.7241. Min Act: -0.1700
Data Index: 7666878 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6929. Min Act: -0.1700
Data Index: 3667729 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6929. Min Act: -0.1700
Data Index: 3316241 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6929. Min Act: -0.1700
Data Index: 5981325 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6616. Min Act: -0.1700
Data Index: 5119658 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6616. Min Act: -0.1700
Data Index: 6585209 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6616. Min Act: -0.1700
Data Index: 170918 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6616. Min Act: -0.1700
Data Index: 5379547 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6304. Min Act: -0.1700
Data Index: 5076270 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6304. Min Act: -0.1700
Data Index: 4817223 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6304. Min Act: -0.1700
Data Index: 3464108 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5991. Min Act: -0.1700
Data Index: 6237429 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5991. Min Act: -0.1700
Data Index: 5254516 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.6304. Min Act: -0.1700
Data Index: 2376129 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5991. Min Act: -0.1700
Data Index: 5919234 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5679. Min Act: -0.1700
Data Index: 5502000 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5679. Min Act: -0.1700
Data Index: 4797861 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7554. Min Range: -5.7554
Max Act: 5.5679. Min Act: -0.1700
Data Index: 924295 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19