Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 716 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3820. Min Range: -7.3820
Max Act: 7.3820. Min Act: -0.1700
Data Index: 6796652 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.6320. Min Act: -0.1700
Data Index: 7929055 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.5382. Min Act: -0.1700
Data Index: 2031966 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.4445. Min Act: -0.1700
Data Index: 2076623 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.4445. Min Act: -0.1700
Data Index: 274236 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.3820. Min Act: -0.1700
Data Index: 7318017 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.3507. Min Act: -0.1700
Data Index: 6524183 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.3195. Min Act: -0.1700
Data Index: 6173985 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.3195. Min Act: -0.1700
Data Index: 6185449 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.2570. Min Act: -0.1700
Data Index: 5826621 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.2570. Min Act: -0.1700
Data Index: 2896867 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.2570. Min Act: -0.1700
Data Index: 4857975 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.2257. Min Act: -0.1700
Data Index: 788923 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.2257. Min Act: -0.1700
Data Index: 5893200 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.2257. Min Act: -0.1700
Data Index: 6470001 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.1945. Min Act: -0.1700
Data Index: 70057 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.1945. Min Act: -0.1700
Data Index: 4045657 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.1632. Min Act: -0.1700
Data Index: 7525430 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.1632. Min Act: -0.1700
Data Index: 2995077 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3820. Min Range: -7.3820
Max Act: 6.1632. Min Act: -0.1700
Data Index: 4632026 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19