Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.9506. Min Act: -0.1700
Data Index: 2260026 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.9031. Min Act: -0.1700
Data Index: 7865690 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.9031. Min Act: -0.1700
Data Index: 4849930 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.9031. Min Act: -0.1700
Data Index: 7865692 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.8396. Min Act: -0.1700
Data Index: 5823158 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.8237. Min Act: -0.1700
Data Index: 7472047 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.8237. Min Act: -0.1700
Data Index: 7865687 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.8078. Min Act: -0.1700
Data Index: 1185680 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.8078. Min Act: -0.1700
Data Index: 8025501 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.7759. Min Act: -0.1700
Data Index: 8365555 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.7599. Min Act: -0.1700
Data Index: 3261754 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.7599. Min Act: -0.1700
Data Index: 7083695 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.7440. Min Act: -0.1700
Data Index: 3775133 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.7120. Min Act: -0.1700
Data Index: 1226480 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.7280. Min Act: -0.1700
Data Index: 4840979 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.7280. Min Act: -0.1700
Data Index: 3775112 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.6960. Min Act: -0.1700
Data Index: 7353130 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.7120. Min Act: -0.1700
Data Index: 7545712 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.7120. Min Act: -0.1700
Data Index: 6179754 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9506. Min Range: -2.9506
Max Act: 2.6960. Min Act: -0.1700
Data Index: 6661269 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19