Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 980 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.6535. Min Act: -0.1700
Data Index: 3530842 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.5909. Min Act: -0.1700
Data Index: 3144354 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.5909. Min Act: -0.1700
Data Index: 5020240 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.5596. Min Act: -0.1700
Data Index: 2673865 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4970. Min Act: -0.1700
Data Index: 6707421 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.5283. Min Act: -0.1700
Data Index: 4399873 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.5283. Min Act: -0.1700
Data Index: 5539477 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.5283. Min Act: -0.1700
Data Index: 5204613 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4970. Min Act: -0.1700
Data Index: 6942276 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.5283. Min Act: -0.1700
Data Index: 3039759 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4656. Min Act: -0.1700
Data Index: 1549132 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4656. Min Act: -0.1700
Data Index: 8811472 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4656. Min Act: -0.1700
Data Index: 6485392 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4656. Min Act: -0.1700
Data Index: 5885085 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4343. Min Act: -0.1700
Data Index: 6230799 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4343. Min Act: -0.1700
Data Index: 31048 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4343. Min Act: -0.1700
Data Index: 5068367 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4343. Min Act: -0.1700
Data Index: 3536901 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4343. Min Act: -0.1700
Data Index: 7412034 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6535. Min Range: -3.6535
Max Act: 3.4343. Min Act: -0.1700
Data Index: 1040873 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19